energy management systems research paper

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Perspective
• Published: 18 October 2022

Machine learning for a sustainable energy future

• Zhenpeng Yao   ORCID: orcid.org/0000-0001-8286-8257 1 , 2 , 3 , 4   na1 ,
• Yanwei Lum   ORCID: orcid.org/0000-0001-7261-2098 5 , 6   na1 ,
• Andrew Johnston 6   na1 ,
• Luis Martin Mejia-Mendoza 2 ,
• Xin Zhou 7 ,
• Yonggang Wen 7 ,
• Alán Aspuru-Guzik   ORCID: orcid.org/0000-0002-8277-4434 2 , 8 ,
• Edward H. Sargent   ORCID: orcid.org/0000-0003-0396-6495 6 &
• Zhi Wei Seh   ORCID: orcid.org/0000-0003-0953-567X 5  

Nature Reviews Materials volume  8 ,  pages 202–215 ( 2023 ) Cite this article

30k Accesses

92 Citations

25 Altmetric

Metrics details

• Computer science

Electrocatalysis

• Energy grids and networks
• Solar cells

Transitioning from fossil fuels to renewable energy sources is a critical global challenge; it demands advances — at the materials, devices and systems levels — for the efficient harvesting, storage, conversion and management of renewable energy. Energy researchers have begun to incorporate machine learning (ML) techniques to accelerate these advances. In this Perspective, we highlight recent advances in ML-driven energy research, outline current and future challenges, and describe what is required to make the best use of ML techniques. We introduce a set of key performance indicators with which to compare the benefits of different ML-accelerated workflows for energy research. We discuss and evaluate the latest advances in applying ML to the development of energy harvesting (photovoltaics), storage (batteries), conversion (electrocatalysis) and management (smart grids). Finally, we offer an overview of potential research areas in the energy field that stand to benefit further from the application of ML.

Similar content being viewed by others

A review of the recent progress in battery informatics

Predicting the state of charge and health of batteries using data-driven machine learning

Fundamental theory on multiple energy resources and related case studies

Introduction.

The combustion of fossil fuels, used to fulfill approximately 80% of the world’s energy needs, is the largest single source of rising greenhouse gas emissions and global temperature 1 . The increased use of renewable sources of energy, notably solar and wind power, is an economically viable path towards meeting the climate goals of the Paris Agreement 2 . However, the rate at which renewable energy has grown has been outpaced by ever-growing energy demand, and as a result the fraction of total energy produced by renewable sources has remained constant since 2000 (ref. 3 ). It is thus essential to accelerate the transition towards sustainable sources of energy 4 . Achieving this transition requires energy technologies, infrastructure and policies that enable and promote the harvest, storage, conversion and management of renewable energy.

In sustainable energy research, suitable material candidates (such as photovoltaic materials) must first be chosen from the combinatorial space of possible materials, then synthesized at a high enough yield and quality for use in devices (such as solar panels). The time frame of a representative materials discovery process is 15–20 years 5 , 6 , leaving considerable room for improvement. Furthermore, the devices have to be optimized for robustness and reproducibility to be incorporated into energy systems (such as in solar farms) 7 , where management of energy usage and generation patterns is needed to further guarantee commercial success.

Here we explore the extent to which machine learning (ML) techniques can help to address many of these challenges 8 , 9 , 10 . ML models can be used to predict specific properties of new materials without the need for costly characterization; they can generate new material structures with desired properties; they can understand patterns in renewable energy usage and generation; and they can help to inform energy policy by optimizing energy management at both device and grid levels.

In this Perspective, we introduce Acc(X)eleration Performance Indicators (XPIs), which can be used to measure the effectiveness of platforms developed for accelerated energy materials discovery. Next, we discuss closed-loop ML frameworks and evaluate the latest advances in applying ML to the development of energy harvesting, storage and conversion technologies, as well as the integration of ML into a smart power grid. Finally, we offer an overview of energy research areas that stand to benefit further from ML.

Performance indicators

Because many reports discuss ML-accelerated approaches for materials discovery and energy systems management, we posit that there should be a consistent baseline from which these reports can be compared. For energy systems management, performance indicators at the device, plant and grid levels have been reported 11 , 12 , yet there are no equivalent counterparts for accelerated materials discovery.

The primary goal in materials discovery is to develop efficient materials that are ready for commercialization. The commercialization of a new material requires intensive research efforts that can span up to two decades: the goal of every accelerated approach should be to accomplish commercialization an order-of-magnitude faster. The materials science field can benefit from studying the case of vaccine development. Historically, new vaccines take 10 years from conception to market 13 . However, after the start of the COVID-19 pandemic, several companies were able to develop and begin releasing vaccines in less than a year. This achievement was in part due to an unprecedented global research intensity, but also to a shift in the technology: after a technological breakthrough in 2008, the cost of sequencing DNA began decreasing exponentially 14 , 15 , enabling researchers to screen orders-of-magnitude more vaccines than was previously possible.

ML for energy technologies has much in common with ML for other fields like biomedicine, sharing the same methodology and principles. However, in practice, ML models for different technologies are exposed to additional unique requirements. For example, ML models for medical applications usually have complex structures that take into account regulatory oversight and ensure the safe development, use and monitoring of systems, which usually does not happen in the energy field 16 . Moreover, data availability varies substantially from field to field; biomedical researchers can work with a relatively large amount of data that energy researchers usually lack. This limited data accessibility can constrain the usage of sophisticated ML models (such as deep learning models) in the energy field. However, adaptation has been quick in all energy subfields, with a rapidly increased number of groups recognizing the importance of statistical methods and starting to use them for various problems. We posit that the use of high-throughput experimentation and ML in materials discovery workflows can result in breakthroughs in accelerating development, but the field first needs a set of metrics with which ML models can be evaluated and compared.

Accelerated materials discovery methods should be judged based on the time it takes for a new material to be commercialized. We recognize that this is not a useful metric for new platforms, nor is it one that can be used to decide quickly which platform is best suited for a particular scenario. We therefore propose here XPIs that new materials discovery platforms should report.

Acceleration factor of new materials, XPI-1

This XPI is evaluated by dividing the number of new materials that are synthesized and characterized per unit time with the accelerated platform by the number of materials that are synthesized and characterized with traditional methods. For example, an acceleration factor of ten means that for a given time period, the accelerated platform can evaluate ten times more materials than a traditional platform. For materials with multiple target properties, researchers should report the rate-limiting acceleration factor.

Number of new materials with threshold performance, XPI-2

This XPI tracks the number of new materials discovered with an accelerated platform that have a performance greater than the baseline value. The selection of this baseline value is critical: it should be something that fairly captures the standard to which new materials need to be compared. As an example, an accelerated platform that seeks to discover new perovskite solar cell materials should track the number of devices made with new materials that have a better performance than the best existing solar cell 17 .

Performance of best material over time, XPI-3

This XPI tracks the absolute performance — whether it is Faradaic efficiency, power conversion efficiency or other — of the best material as a function of time. For the accelerated framework, the evolution of the performance should increase faster than the performance obtained by traditional methods 18 .

Repeatability and reproducibility of new materials, XPI-4

This XPI seeks to ensure that the new materials discovered are consistent and repeatable: this is a key consideration to screen out materials that would fail at the commercialization stage. The performance of a new material should not vary by more than x % of its mean value (where x is the standard error): if it does, this material should not be included in either XPI-2 (number of new materials with threshold performance) or XPI-3 (performance of best material over time).

Human cost of the accelerated platform, XPI-5

This XPI reports the total costs of the accelerated platform. This should include the total number of researcher hours needed to design and order the components for the accelerated system, develop the programming and robotic infrastructure, develop and maintain databases used in the system and maintain and run the accelerated platform. This metric would provide researchers with a realistic estimate of the resources required to adapt an accelerated platform for their own research.

Use of the XPIs

Each of these XPIs can be measured for computational, experimental or integrated accelerated systems. Consistently reporting each of these XPIs as new accelerated platforms are developed will allow researchers to evaluate the growth of these platforms and will provide a consistent metric by which different platforms can be compared. As a demonstration, we applied the XPIs to evaluate the acceleration performance of several typical platforms: Edisonian-like trial-test, robotic photocatalysis development 19 and design of a DNA-encoded-library-based kinase inhibitor 20 (Table  1 ). To obtain a comprehensive performance estimate, we define one overall acceleration score S adhering to the following rules. The dependent acceleration factors (XPI-1 and XPI-2), which function in a synergetic way, are added together to reflect their contribution as a whole. The independent acceleration factors (XPI-3, XPI-4 and XPI-5), which may function in a reduplicated way, are multiplied together to value their contributions respectively. As a result, the overall acceleration score can be calculated as S  = (XPI-1 + XPI-2) × XPI-3 × XPI-4 ÷ XPI-5. As the reference, the Edisonian-like approach has a calculated overall XPIs score of around 1, whereas the most advanced method, the DNA-encoded-library-based drug design, exhibits an overall XPIs score of 10 7 . For the sustainability field, the robotic photocatalysis platform has an overall XPIs score of 10 5 .

For energy systems, the most frequently reported XPI is the acceleration factor, in part because it is deterministic, but also because it is easy to calculate at the end of the development of a workflow. In most cases, we expect that authors report the acceleration factor only after completing the development of the platform. Reporting the other suggested XPIs will provide researchers with a better sense of both the time and human resources required to develop the platform until it is ready for publication. Moving forward, we hope that other researchers adopt the XPIs — or other similar metrics — to allow for fair and consistent comparison between the different methods and algorithms that are used to accelerate materials discovery.

Closed-loop ML for materials discovery

The traditional approach to materials discovery is often Edisonian-like, relying on trial and error to develop materials with specific properties. First, a target application is identified, and a starting pool of possible candidates is selected (Fig.  1a ). The materials are then synthesized and incorporated into a device or system to measure their properties. These results are then used to establish empirical structure–property relationships, which guide the next round of synthesis and testing. This slow process goes through as many iterations as required and each cycle can take several years to complete.

a | Traditional Edisonian-like approach, which involves experimental trial and error. b | High-throughput screening approach involving a combination of theory and experiment. c | Machine learning (ML)-driven approach whereby theoretical and experimental results are used to train a ML model for predicting structure–property relationships. d | ML-driven approach for property-directed and automatic exploration of the chemical space using optimization ML (such as genetic algorithms or generative models) that solve the ‘inverse’ design problem.

A computation-driven, high-throughput screening strategy (Fig.  1b ) offers a faster turnaround. To explore the overall vast chemical space (~10 60 possibilities), human intuition and expertise can be used to create a library with a substantial number of materials of interest (~10 4 ). Theoretical calculations are carried out on these candidates and the top performers (~10 2 candidates) are then experimentally verified. With luck, the material with the desired functionality is ‘discovered’. Otherwise, this process is repeated in another region of the chemical space. This approach can still be very time-consuming and computationally expensive and can only sample a small region of the chemical space.

ML can substantially increase the chemical space sampled, without costing extra time and effort. ML is data-driven, screening datasets to detect patterns, which are the physical laws that govern the system. In this case, these laws correspond to materials structure–property relationships. This workflow involves high-throughput virtual screening (Fig.  1c ) and begins by selecting a larger region (~10 6 ) of the chemical space of possibilities using human intuition and expertise. Theoretical calculations are carried out on a representative subset (~10 4 candidates) and the results are used for training a discriminative ML model. The model can then be used to make predictions on the other candidates in the overall selected chemical space 9 . The top ~10 2 candidates are experimentally verified, and the results are used to improve the predictive capabilities of the model in an iterative loop. If the desired material is not ‘discovered’, the process is repeated on another region of the chemical space.

An improvement on the previous approaches is a framework that requires limited human intuition or expertise to direct the chemical space search: the automated virtual screening approach (Fig.  1d ). To begin with, a region of the chemical space is picked at random to initiate the process. Thereafter, this process is similar to the previous approach, except that the computational and experimental data is also used to train a generative learning model. This generative model solves the ‘inverse’ problem: given a required property, the goal is to predict an ideal structure and composition in the chemical space. This enables a directed, automated search of the chemical space, towards the goal of ‘discovering’ the ideal material 8 .

ML for energy

ML has so far been used to accelerate the development of materials and devices for energy harvesting (photovoltaics), storage (batteries) and conversion (electrocatalysis), as well as to optimize power grids. Besides all the examples discussed here, we summarize the essential concepts in ML (Box  1 ), the grand challenges in sustainable materials research (Box  2 ) and the details of key studies (Table  2 ).

Box 1 Essential concepts in ML

With the availability of large datasets 122 , 125 and increased computing power, various machine learning (ML) algorithms have been developed to solve diverse problems in energy. Below, we provide a brief overview of the types of problem that ML can solve in energy technology, and we then summarize the status of ML-driven energy research. More detailed information about the nuts and bolts of ML techniques can be found in previous reviews 173 , 174 , 175 .

Property prediction

Supervised learning models are predictive (or discriminative) models that are given a datapoint x , and seek to predict a property y (for example, the bandgap 27 ) after being trained on a labelled dataset. The property y can be either continuous or discrete. These models have been used to aid or even replace physical simulations or measurements under certain circumstances 176 , 177 .

Generative materials design

Unsupervised learning models are generative models that can generate or output new examples x ′ (such as new molecules 104 ) after being trained on an unlabelled dataset. This generation of new examples can be further enhanced with additional information (physical properties) to condition or bias the generative process, allowing the models to generate examples with improved properties and leading to the property-to-structure approach called inverse design 52 , 178 .

Self-driving laboratories

Self-driving or autonomous laboratories 19 use ML models to plan and perform experiments, including the automation of retrosynthesis analysis (such as in reinforcement-learning-aided synthesis planning 124 , 179 ), prediction of reaction products (such as in convolutional neural networks (CNNs) for reaction prediction 137 , 138 ) and reaction condition optimization (such as in robotic workflows optimized by active learning 19 , 160 , 180 , 181 , 182 , 183 ). Self-driving laboratories, which use active learning for iterating through rounds of synthesis and measurements, are a key component in the closed-loop inverse design 52 .

Aiding characterization

ML models have been used to aid the quantitative or qualitative analysis of experimental observations and measurements, including assisting in the determination of crystal structure from transmission electron microscopy images 184 , identifying coordination environment 81 and structural transition 83 from X-ray absorption spectroscopy and inferring crystal symmetry from electron diffraction 176 .

Accelerating theoretical computations

ML models can enable otherwise intractable simulations by reducing the computational cost (processor core amount and time) for systems with increased length and timescales 69 , 70 and providing potentials and functionals for complex interactions 68 .

Optimizing system management

ML models can aid the management of energy systems at the device or grid power level by predicting lifetimes (such as battery life 43 , 44 ), adapting to new loads (such as in long short-term memory for building load prediction 95 ) and optimizing performance (such as in reinforcement learning for smart grid control 94 ).

Box 2 Grand challenges in energy materials research

Photovoltaics.

Discover non-toxic (Pd- and Cd-free) materials with good optoelectronic properties

Identify and minimize materials defects in light-absorbing materials

Design effective recombination-layer materials for tandem solar cells

Develop materials design strategies for long-term operational stability 125

Develop (hole/electron) transport materials with high carrier mobility 125

Optimize cell structure for maximum light absorption and minimum use of active materials

Tune materials bandgaps for optimal solar-harvesting performance under complex operation conditions 21 , 22

Develop Earth-abundant cathode materials (Co-free) with high reversibility and charge capacity 4

Design electrolytes with wider electrochemical windows and high conductivity 4

Identify electrolyte systems to boost battery performance and lifetime 4

Discover new molecules for redox flow batteries with suitable voltage 4

Understand correlation between defect growth in battery materials and overall degradation process of battery components

Tune operando (dis)charging protocol for minimized capacity loss, (dis)charging rate and optimal battery life under diversified conditions 7 , 53

Design materials with optimal adsorption energy for maximized catalytic activity 60 , 61

Identify and study active sites on catalytic materials 58

Engineer catalytic materials for extended durability 58 , 60 , 61

Identify a fuller set of materials descriptors that relate to catalytic activity 60 , 61

Engineer multiple catalytic functionalities into the same material 60 , 61

Design multiscale electrode structures for optimized catalytic activity

Correlate atomistic contamination and growth of catalyst particles with electrode degradation process

Tune operando (dis)charging protocol for minimized capacity loss and optimal cell life

ML is accelerating the discovery of new optoelectronic materials and devices for photovoltaics, but major challenges are still associated with each step.

Photovoltaics materials discovery

One materials class for which ML has proved particularly effective is perovskites, because these materials have a vast chemical space from which the constituents may be chosen. Early representations of perovskite materials for ML were atomic-feature representations, in which each structure is encoded as a fixed-length vector comprised of an average of certain atomic properties of the atoms in the crystal structure 21 , 22 . A similar technique was used to predict new lead-free perovskite materials with the proper bandgap for solar cells 23 (Fig.  2a ). These representations allowed for high accuracy but did not account for any spatial relation between atoms 24 , 25 . Materials systems can also be represented as images 26 or as graphs 27 , enabling the treatment of systems with diverse number of atoms. The latter representation is particularly compelling, as perovskites, particularly organic–inorganic perovskites, have crystal structures that incorporate a varying number of atoms, and the organic molecules can vary in size.

a | Energy harvesting 23 . b | Energy storage 38 . c | Energy conversion 76 . d | Energy management 93 . ICSD, Inorganic Crystal Structure Database; ML, machine learning.

Although bandgap prediction is an important first step, this parameter alone is not sufficient to indicate a useful optoelectronic material; other parameters, including electronic defect density and stability, are equally important. Defect energies are addressable with computational methods, but the calculation of defects in structures is extremely computationally expensive, which inhibits the generation of a dataset of defect energies from which an ML model can be trained. To expedite the high-throughput calculation of defect energies, a Python toolkit has been developed 28 that will be pivotal in building a database of defect energies in semiconductors. Researchers can then use ML to predict both the formation energy of defects and the energy levels of these defects. This knowledge will ensure that the materials selected from high-throughput screening will not only have the correct bandgap but will also either be defect-tolerant or defect-resistant, finding use in commercial optoelectronic devices.

Even without access to a large dataset of experimental results, ML can accelerate the discovery of optoelectronic materials. Using a self-driving laboratory approach, the number of experiments required to optimize an organic solar cell can be reduced from 500 to just 60 (ref. 29 ). This robotic synthesis method accelerates the learning rate of the ML models and drastically reduces the cost of the chemicals needed to run the optimization.

Solar device structure and fabrication

Photovoltaic devices require optimization of layers other than the active layer to maximize performance. One component is the top transparent conductive layer, which needs to have both high optical transparency and high electronic conductivity 30 , 31 . A genetic algorithm that optimized the topology of a light-trapping structure enabled a broadband absorption efficiency of 48.1%, which represents a more than threefold increase over the Yablonovitch limit, the 4 n 2 factor (where n is the refractive index of the material) theoretical limit for light trapping in photovoltaics 32 .

A universal standard irradiance spectrum is usually used by researchers to determine optimal bandgaps for solar cell operation 33 . However, actual solar irradiance fluctuates based on factors such as the position of the Sun, atmospheric phenomena and the season. ML can reduce yearly spectral sets into a few characteristic spectra 33 , allowing for the calculation of optimal bandgaps for real-world conditions.

To optimize device fabrication, a CNN was used to predict the current–voltage characteristics of as-cut Si wafers based on their photoluminescence images 34 . Additionally, an artificial neural network was used to predict the contact resistance of metallic front contacts for Si solar cells, which is critical for the manufacturing process 35 .

Although successful, these studies appear to be limited to optimizing structures and processes that are already well established. We suggest that, in future work, ML could be used to augment simulations, such as the multiphysics models for solar cells. Design of device architecture could begin from such simulation models, coupled with ML in an iterative process to quickly optimize design and reduce computational time and cost. In addition, optimal conditions for the scaling-up of device area and fabrication processes are likely to be very different from those for laboratory-scale demonstrations. However, determining these optimal conditions could be expensive in terms of materials cost and time, owing to the need to construct much larger devices. In this regard, ML, together with the strategic design of experiments, could greatly accelerate the optimization of process conditions (such as the annealing temperatures and solvent choice).

Electrochemical energy storage

Electrochemical energy storage is an essential component in applications such as electric vehicles, consumer electronics and stationary power stations. State-of-the-art electrochemical energy storage solutions have varying efficacy in different applications: for example, lithium-ion batteries exhibit excellent energy density and are widely used in electronics and electric vehicles, whereas redox flow batteries have drawn substantial attention for use in stationary power storage. ML approaches have been widely employed in the field of batteries, including for the discovery of new materials such as solid-state ion conductors 36 , 37 , 38 (Fig.  2b ) and redox active electrolytes for redox flow batteries 39 . ML has also aided battery management, for example, through state-of-charge determination 40 , state-of-health evaluation 41 , 42 and remaining-life prediction 43 , 44 .

Electrode and electrolyte materials design

Layered oxide materials, such as LiCoO 2 or LiNi x Mn y Co 1- x - y O 2 , have been used extensively as cathode materials for alkali metal-ion (Li/Na/K) batteries. However, developing new Li-ion battery materials with higher operating voltages, enhanced energy densities and longer lifetimes is of paramount interest. So far, universal design principles for new battery materials remain undefined, and hence different approaches have been explored. Data from the Materials Project have been used to model the electrode voltage profile diagrams for different materials in alkali metal-ion batteries (Na and K) 45 , leading to the proposition of 5,000 different electrode materials with appropriate moderate voltages. ML was also employed to screen 12,000 candidates for solid Li-ion batteries, resulting in the discovery of ten new Li-ion conducting materials 46 , 47 .

Flow batteries consist of active materials dissolved in electrolytes that flow into a cell with electrodes that facilitate redox reactions. Organic flow batteries are of particular interest. In flow batteries, the solubility of the active material in the electrolyte and the charge/discharge stability dictate performance. ML methods have explored the chemical space to find suitable electrolytes for organic redox flow batteries 48 , 49 . Furthermore, a multi-kernel-ridge regression method accelerated the discovery of active organic molecules using multiple feature training 48 . This method also helped in predicting the solubility dependence of anthraquinone molecules with different numbers and combinations of sulfonic and hydroxyl groups on pH. Future opportunities lie in the exploration of large combinatorial spaces for the inverse design of high-entropy electrodes 50 and high-voltage electrolytes 51 . To this end, deep generative models can assist the discovery of new materials based on the simplified molecular input line entry system (SMILES) representation of molecules 52 .

Battery device and stack management

A combination of mechanistic and semi-empirical models is currently used to estimate capacity and power loss in lithium-ion batteries. However, the models are applicable only to specific failure mechanisms or situations and cannot predict the lifetimes of batteries at the early stages of usage. By contrast, mechanism-agnostic models based on ML can accurately predict battery cycle life, even at an early stage of a battery’s life 43 . A combined early-prediction and Bayesian optimization model has been used to rapidly identify the optimal charging protocol with the longest cycle life 44 . ML can be used to accelerate the optimization of lithium-ion batteries for longer lifetimes 53 , but it remains to be seen whether these models can be generalized to different battery chemistries 54 .

ML methods can also predict important properties of battery storage facilities. A neural network was used to predict the charge/discharge profiles in two types of stationary battery systems, lithium iron phosphate and vanadium redox flow batteries 55 . Battery power management techniques must also consider the uncertainty and variability that arise from both the environment and the application. An iterative Q -learning ( reinforcement learning ) method was also designed for battery management and control in smart residential environments 56 . Given the residential load and the real-time electricity rate, the method is effective at optimizing battery charging/discharging/idle cycles. Discriminative neural network-based models can also optimize battery usage in electric vehicles 57 .

Although ML is able to predict the lifetime of batteries, the underlying degradation mechanisms are difficult to identify and correlate to the state of health and lifetime. To this end, incorporation of domain knowledge into a hybrid physics-based ML model can provide insight and reduce overfitting 53 . However, incorporating the physics of battery degradation processes into a hybrid model remains challenging; representation of electrode materials that encode both compositional and structural information is far from trivial. Validation of these models also requires the development of operando characterization techniques, such as liquid-phase transmission electron microscopy and ambient-pressure X-ray absorption spectroscopy (XAS), that reflect true operating conditions as closely as possible 54 . Ideally, these characterization techniques should be carried out in a high-throughput manner, using automated sample changers, for example, in order to generate large datasets for ML.

Electrocatalysts

Electrocatalysis enables the conversion of simple feedstocks (such as water, carbon dioxide and nitrogen) into valuable chemicals and/or fuels (such as hydrogen, hydrocarbons and ammonia), using renewable energy as an input 58 . The reverse reactions are also possible in a fuel cell, and hydrogen can be consumed to produce electricity 59 . Active and selective electrocatalysts must be developed to improve the efficiency of these reactions 60 , 61 . ML has been used to accelerate electrocatalyst development and device optimization.

Electrocatalyst materials discovery

The most common descriptor of catalytic activity is the adsorption energy of intermediates on a catalyst 61 , 62 . Although these adsorption energies can be calculated using density functional theory (DFT), catalysts possess multiple surface binding sites, each with different adsorption energies 63 . The number of possible sites increases dramatically if alloys are considered, and thus becomes intractable with conventional means 64 .

DFT calculations are critical for the search of electrocatalytic materials 65 and efforts have been made to accelerate the calculations and to reduce their computational cost by using surrogate ML models 66 , 67 , 68 , 69 . Complex reaction mechanisms involving hundreds of possible species and intermediates can also be simplified using ML, with a surrogate model predicting the most important reaction steps and deducing the most likely reaction pathways 70 . ML can also be used to screen for active sites across a random, disordered nanoparticle surface 71 , 72 . DFT calculations are performed on only a few representative sites, which are then used to train a neural network to predict the adsorption energies of all active sites.

Catalyst development can benefit from high-throughput systems for catalyst synthesis and performance evaluation 73 , 74 . An automatic ML-driven framework was developed to screen a large intermetallic chemical space for CO 2 reduction and H 2 evolution 75 . The model predicted the adsorption energy of new intermetallic systems and DFT was automatically performed on the most promising candidates to verify the predictions. This process went on iteratively in a closed feedback loop. 131 intermetallic surfaces across 54 alloys were ultimately identified as promising candidates for CO 2 reduction. Experimental validation 76 with Cu–Al catalysts yielded an unprecedented Faradaic efficiency of 80% towards ethylene at a high current density of 400 mA cm – 2 (Fig.  2c ).

Because of the large number of properties that electrocatalysts may possess (such as shape, size and composition), it is difficult to do data mining on the literature 77 . Electrocatalyst structures are complex and difficult to characterize completely; as a result, many properties may not be fully characterized by research groups in their publications. To avoid situations in which potentially promising compositions perform poorly as a result of non-ideal synthesis or testing conditions, other factors (such as current density, particle size and pH value) that affect the electrocatalyst performance must be kept consistent. New approaches such as carbothermal shock synthesis 78 , 79 may be a promising avenue, owing to its propensity to generate uniformly sized and shaped alloy nanoparticles, regardless of composition.

XAS is a powerful technique, especially for in situ measurements, and has been widely employed to gain crucial insight into the nature of active sites and changes in the electrocatalyst over time 80 . Because the data analysis relies heavily on human experience and expertise, there has been interest in developing ML tools for interpreting XAS data 81 . Improved random forest models can predict the Bader charge (a good approximation of the total electronic charge of an atom) and nearest-neighbour distances, crucial factors that influence the catalytic properties of the material 82 . The extended X-ray absorption fine structure (EXAFS) region of XAS spectra is known to contain information on bonding environments and coordination numbers. Neural networks can be used to automatically interpret EXAFS data 83 , permitting the identification of the structure of bimetallic nanoparticles using experimental XAS data, for example 84 . Raman and infrared spectroscopy are also important tools for the mechanistic understanding of electrocatalysis. Together with explainable artificial intelligence (AI), which can relate the results to underlying physics, these analyses could be used to discover descriptors hidden in spectra that could lead to new breakthroughs in electrocatalyst discovery and optimization.

Fuel cell and electrolyser device management

A fuel cell is an electrochemical device that can be used to convert the chemical energy of a fuel (such as hydrogen) into electrical energy. An electrolyser transforms electrical energy into chemical energy (such as in water splitting to generate hydrogen). ML has been used to optimize and manage their performance, predict degradation and device lifetime as well as detect and diagnose faults. Using a hybrid method consisting of an extreme learning machine, genetic algorithms and wavelet analysis, the degradation in proton-exchange membrane fuel cells has been predicted 85 , 86 . Electrochemical impedance measurements used as input for an artificial neural network have enabled fault detection and isolation in a high-temperature stack of proton-exchange membrane fuel cells 87 , 88 .

ML approaches can also be employed to diagnose faults, such as fuel and air leakage issues, in solid oxide fuel cell stacks. Artificial neural networks can predict the performance of solid oxide fuel cells under different operating conditions 89 . In addition, ML has been applied to optimize the performance of solid oxide electrolysers, for CO 2 /H 2 O reduction 90 , and chloralkali electrolysers 91 .

In the future, the use of ML for fuel cells could be combined with multiscale modelling to improve their design, for example to minimize Ohmic losses and optimize catalyst loading. For practical applications, fuel cells may be subject to fluctuations in energy output requirements (for example, when used in vehicles). ML models could be used to determine the effects of such fluctuations on the long-term durability and performance of fuel cells, similar to what has been done for predicting the state of health and lifetime for batteries. Furthermore, it remains to be seen whether the ML techniques for fuel cells can be easily generalized to electrolysers and vice versa, using transfer learning for example, given that they are essentially reactions in reverse.

Smart power grids

A power grid is responsible for delivering electrical energy from producers (such as power plants and solar farms) to consumers (such as homes and offices). However, energy fluctuations from intermittent renewable energy generators can render the grid vulnerable 92 . ML algorithms can be used to optimize the automatic generation control of power grids, which controls the power output of multiple generators in an energy system. For example, when a relaxed deep learning model was used as a unified timescale controller for the automatic generation control unit, the total operational cost was reduced by up to 80% compared with traditional heuristic control strategies 93 (Fig.  2d ). A smart generation control strategy based on multi-agent reinforcement learning was found to improve the control performance by around 10% compared with other ML algorithms 94 .

Accurate demand and load prediction can support decision-making operations in energy systems for proper load scheduling and power allocation. Multiple ML methods have been proposed to precisely predict the demand load: for example, long short-term memory was used to successfully and accurately predict hourly building load 95 . Short-term load forecasting of diverse customers (such as retail businesses) using a deep neural network and cross-building energy demand forecasting using a deep belief network have also been demonstrated effectively 96 , 97 .

Demand-side management consists of a set of mechanisms that shape consumer electricity consumption by dynamically adjusting the price of electricity. These include reducing (peak shaving), increasing (load growth) and rescheduling (load shifting) the energy demand, which allows for flexible balancing of renewable electricity generation and load 98 . A reinforcement-learning-based algorithm resulted in substantial cost reduction for both the service provider and customer 99 . A decentralized learning-based residential demand scheduling technique successfully shifted up to 35% of the energy demand to periods of high wind availability, substantially saving power costs compared with the unscheduled energy demand scenario 100 . Load forecasting using a multi-agent approach integrates load prediction with reinforcement learning algorithms to shift energy usage (for example, to different electrical devices in a household) for its optimization 101 . This approach reduced peak usage by more than 30% and increased off-peak usage by 50%, reducing the cost and energy losses associated with energy storage.

Opportunities for ML in renewable energy

ML provides the opportunity to enable substantial further advances in different areas of the energy materials field, which share similar materials-related challenges (Fig.  3 ). There are also grand challenges for ML application in smart grid and policy optimization.

a | Energy materials present additional modelling challenges. Machine learning (ML) could help in the representation of structurally complex structures, which can include disordering, dislocations and amorphous phases. b | Flexible models that scale efficiently with varied dataset sizes are in demand, and ML could help to develop robust predictive models. The yellow dots stand for the addition of unreliable datasets that could harm the prediction accuracy of the ML model. c | Synthesis route prediction remains to be solved for the design of a novel material. In the ternary phase diagram, the dots stand for the stable compounds in that corresponding phase space and the red dot for the targeted compound. Two possible synthesis pathways are compared for a single compound. The score obtained would reflect the complexity, cost and so on of one synthesis pathway. d | ML-aided phase degradation prediction could boost the development of materials with enhanced cyclability. The shaded region represents the rocksalt phase, which grows inside the layered phase. The arrow marks the growth direction. e | The use of ML models could help in optimizing energy generation and energy consumption. Automating the decision-making processes associated with dynamic power supplies using ML will make the power distribution more efficient. f | Energy policy is the manner in which an entity (for example, a government) addresses its energy issues, including conversion, distribution and utilization, where ML could be used to optimize the corresponding economy.

Materials with novel geometries

A ML representation is effective when it captures the inherent properties of the system (such as its physical symmetries) and can be utilized in downstream ancillary tasks, such as transfer learning to new predictive tasks, building new knowledge using visualization or attribution and generating similar data distributions with generative models 102 .

For materials, the inputs are molecules or crystal structures whose physical properties are modelled by the Schrödinger equation. Designing a general representation of materials that reflects these properties is an ongoing research problem. For molecular systems, several representations have been used successfully, including fingerprints 103 , SMILES 104 , self-referencing embedded strings (SELFIES) 105 and graphs 106 , 107 , 108 . Representing crystalline materials has the added complexity of needing to incorporate periodicity in the representation. Methods like the smooth overlap of atomic positions 109 , Voronoi tessellation 110 , 111 , diffraction images 112 , multi-perspective fingerprints 113 and graph-based algorithms 27 , 114 have been suggested, but typically lack the capability for structure reconstruction.

Complex structural systems found in energy materials present additional modelling challenges (Fig.  3a ): a large number of atoms (such as in reticular frameworks or polymers), specific symmetries (such as in molecules with a particular space group and for reticular frameworks belonging to a certain topology), atomic disordering, partial occupancy, or amorphous phases (leading to an enormous combinatorial space), defects and dislocations (such as interfaces and grain boundaries) and low-dimensionality materials (as in nanoparticles). Reduction approximations alleviate the first issue (using, for example, RFcode for reticular framework representation) 8 , but the remaining several problems warrant intensive future research efforts.

Self- supervised learning , which seeks to lever large amounts of synthetic labels and tasks to continue learning without experimental labels 115 , multi-task learning 116 , in which multiple material properties can be modelled jointly to exploit correlation structure between properties, and meta-learning 117 , which looks at strategies that allow models to perform better in new datasets or in out-of-distribution data, all offer avenues to build better representations. On the modelling front, new advances in attention mechanisms 118 , 119 , graph neural networks 120 and equivariant neural networks 121 expand our range of tools with which to model interactions and expected symmetries.

Robust predictive models

Predictive models are the first step when building a pipeline that seeks materials with desired properties. A key component for building these models is training data; more data will often translate into better-performing models, which in turn will translate into better accuracy in the prediction of new materials. Deep learning models tend to scale more favourably with dataset size than traditional ML approaches (such as random forests). Dataset quality is also essential. However, experiments are usually conducted under diverse conditions with large variation in untracked variables (Fig.  3b ). Additionally, public datasets are more likely to suffer from publication bias, because negative results are less likely to be published even though they are just as important as positive results when training statistical models 122 .

Addressing these issues require transparency and standardization of the experimental data reported in the literature. Text and natural language processing strategies could then be employed to extract data from the literature 77 . Data should be reported with the belief that it will eventually be consolidated in a database, such as the MatD3 database 123 . Autonomous laboratory techniques will help to address this issue 19 , 124 . Structured property databases such as the Materials Project 122 and the Harvard Clean Energy Project 125 can also provide a large amount of data. Additionally, different energy fields — energy storage, harvesting and conversion — should converge upon a standard and uniform way to report data. This standard should be continuously updated; as researchers continue to learn about the systems they are studying, conditions that were previously thought to be unimportant will become relevant.

New modelling approaches that work in low-data regimes, such as data-efficient models, dataset-building strategies (active sampling) 126 and data-augmentation techniques, are also important 127 . Uncertainty quantification , data efficiency, interpretability and regularization are important considerations that improve the robustness of ML models. These considerations relate to the notion of generalizability: predictions should generalize to a new class of materials that is out of the distribution of the original dataset. Researchers can attempt to model how far away new data points are from the training set 128 or the variability in predicted labels with uncertainty quantification 129 . Neural networks are a flexible model class, and often models can be underspecified 130 . Incorporating regularization, inductive biases or priors can boost the credibility of a model. Another way to create trustable models could be to enhance the interpretability of ML algorithms by deriving feature relevance and scoring their importance 131 . This strategy could help to identify potential chemically meaningful features and form a starting point for understanding latent factors that dominate material properties. These techniques can also identify the presence of model bias and overfitting, as well as improving generalization and performance 132 , 133 , 134 .

Stable and synthesizable new materials

The formation energy of a compound is used to estimate its stability and synthesizability 135 , 136 . Although negative values usually correspond to stable or synthesizable compounds, slightly positive formation energies below a limit lead to metastable phases with unclear synthesizability 137 , 138 . This is more apparent when investigating unexplored chemical spaces with undetermined equilibrium ground states; yet often the metastable phases exhibit superior properties, as seen in photovoltaics 136 , 139 and ion conductors 140 , for example. It is thus of interest to develop a method to evaluate the synthesizability of metastable phases (Fig.  3c ). Instead of estimating the probability that a particular phase can be synthesized, one can instead evaluate its synthetic complexity using ML. In organic chemistry, synthesis complexity is evaluated according to the accessibility of the phases’ synthesis route 141 or precedent reaction knowledge 142 . Similar methodologies can be applied to the inorganic field with the ongoing design of automated synthesis-planning algorithms for inorganic materials 143 , 144 .

Synthesis and evaluation of a new material alone does not ensure that material will make it to market; material stability is a crucial property that takes a long time to evaluate. Degradation is a generally complex process that occurs through the loss of active matter or growth of inactive phases (such as the rocksalt phases formed in layered Li-ion battery electrodes 145 (Fig.  3d ) or the Pt particle agglomeration in fuel cells 146 ) and/or propagation of defects (such as cracks in cycled battery electrode 147 ). Microscopies such as electron microscopy 148 and simulations such as continuum mechanics modelling 149 are often used to investigate growth and propagation dynamics (that is, phase boundary and defect surface movements versus time). However, these techniques are usually expensive and do not allow rapid degradation prediction. Deep learning techniques such as convolutional neural networks and recurrent neural networks may be able to predict the phase boundary and/or defect pattern evolution under certain conditions after proper training 150 . Similar models can then be built to understand multiple degradation phenomena and aid the design of materials with improved cycle life.

Optimized smart power grids

A promising prospect of ML in smart grids is automating the decision-making processes that are associated with dynamic power supplies to distribute power most efficiently (Fig.  3e ). Practical deployment of ML technologies into physical systems remains difficult because of data scarcity and the risk-averse mindset of policymakers. The collection of and access to large amounts of diverse data is challenging owing to high cost, long delays and concerns over compliance and security 151 . For instance, to capture the variation of renewable resources owing to peak or off-peak and seasonal attributes, long-term data collections are implemented for periods of 24 hours to several years 152 . Furthermore, although ML algorithms are ideally supposed to account for all uncertainties and unpredictable situations in energy systems, the risk-adverse mindset in the energy management industry means that implementation still relies on human decision-making 153 .

An ML-based framework that involves a digital twin of the physical system can address these problems 154 , 155 . The digital twin represents the digitalized cyber models of the physical system and can be constructed from physical laws and/or ML models trained using data sampled from the physical system. This approach aims to accurately simulate the dynamics of the physical system, enabling relatively fast generation of large amounts of high-quality synthetic data at low cost. Notably, because ML model training and validation is performed on the digital twin, there is no risk to the actual physical system. Based on the prediction results, suitable actions can be suggested and then implemented in the physical system to ensure stability and/or improve system operation.

Policy optimization

Finally, research is generally focused on one narrow aspect of a larger problem; we argue that energy research needs a more integrated approach 156 (Fig.  3f ). Energy policy is the manner in which an entity, such as the government, addresses its energy issues, including conversion, distribution and utilization. ML has been used in the fields of energy economics finance for performance diagnostics (such as for oil wells), energy generation (such as wind power) and consumption (such as power load) forecasts and system lifespan (such as battery cell life) and failure (such as grid outage) prediction 157 . They have also been used for energy policy analysis and evaluation (for example, for estimating energy savings). A natural extension of ML models is to use them for policy optimization 158 , 159 , a concept that has not yet seen widespread use. We posit that the best energy policies — including the deployment of the newly discovered materials — can be improved and augmented with ML and should be discussed in research reporting accelerated energy technology platforms.

Conclusions

To summarize, ML has the potential to enable breakthroughs in the development and deployment of sustainable energy techniques. There have been remarkable achievements in many areas of energy technology, from materials design and device management to system deployment. ML is particularly well suited to discovering new materials, and researchers in the field are expecting ML to bring up new materials that may revolutionize the energy industry. The field is still nascent, but there is conclusive evidence that ML is at least able to expose the same trends that human researchers have noticed over decades of research. The ML field itself is still seeing rapid development, with new methodologies being reported daily. It will take time to develop and adopt these methodologies to solve specific problems in materials science. We believe that for ML to truly accelerate the deployment of sustainable energy, it should be deployed as a tool, similar to a synthesis procedure, characterization equipment or control apparatus. Researchers using ML to accelerate energy technology discovery should judge the success of the method primarily on the advances it enables. To this end, we have proposed the XPIs and some areas in which we hope to see ML deployed.

Davidson, D. J. Exnovating for a renewable energy transition. Nat. Energy 4 , 254–256 (2019).

Article   Google Scholar  

Horowitz, C. A. Paris agreement. Int. Leg. Mater. 55 , 740–755 (2016).

International Energy Agency 2018 World Energy Outlook: Executive Summary https://www.iea.org/reports/world-energy-outlook-2018 (OECD/IEA, 2018).

Chu, S., Cui, Y. & Liu, N. The path towards sustainable energy. Nat. Mater. 16 , 16–22 (2017).

Maine, E. & Garnsey, E. Commercializing generic technology: the case of advanced materials ventures. Res. Policy 35 , 375–393 (2006).

De Luna, P., Wei, J., Bengio, Y., Aspuru-Guzik, A. & Sargent, E. Use machine learning to find energy materials. Nature 552 , 23–27 (2017).

Wang, H., Lei, Z., Zhang, X., Zhou, B. & Peng, J. A review of deep learning for renewable energy forecasting. Energy Convers. Manag. 198 , 111799–111814 (2019).

Yao, Z. et al. Inverse design of nanoporous crystalline reticular materials with deep generative models. Nat. Mach. Intell. 3 , 76–86 (2021).

Rosen, A. S. et al. Machine learning the quantum-chemical properties of metal–organic frameworks for accelerated materials discovery. Matter 4 , 1578–1597 (2021).

Article   CAS   Google Scholar  

Jordan, M. I. & Mitchell, T. M. Machine learning: trends, perspectives, and prospects. Science 349 , 255–260 (2015).

Personal, E., Guerrero, J. I., Garcia, A., Peña, M. & Leon, C. Key performance indicators: a useful tool to assess Smart Grid goals. Energy 76 , 976–988 (2014).

Helmus, J. & den Hoed, R. Key performance indicators of charging infrastructure. World Electr. Veh. J. 8 , 733–741 (2016).

Struck, M.-M. Vaccine R&D success rates and development times. Nat. Biotechnol. 14 , 591–593 (1996).

Moore, G. E. Cramming more components onto integrated circuits. Electronics 38 , 114–116 (1965).

Google Scholar  

Wetterstrand, K. A. DNA sequencing costs: data. NHGRI Genome Sequencing Program (GSP) www.genome.gov/sequencingcostsdata (2020).

Rajkomar, A., Dean, J. & Kohane, I. Machine learning in medicine. N. Engl. J. Med. 380 , 1347–1358 (2019).

Jeong, J. et al. Pseudo-halide anion engineering for α-FAPbI3 perovskite solar cells. Nature 592 , 381–385 (2021).

NREL. Best research-cell efficiency chart. NREL https://www.nrel.gov/pv/cell-efficiency.html (2021).

Burger, B. et al. A mobile robotic chemist. Nature 583 , 237–241 (2020).

Clark, M. A. et al. Design, synthesis and selection of DNA-encoded small-molecule libraries. Nat. Chem. Biol. 5 , 647–654 (2009).

Pilania, G., Gubernatis, J. E. & Lookman, T. Multi-fidelity machine learning models for accurate bandgap predictions of solids. Comput. Mater. Sci. 129 , 156–163 (2017).

Pilania, G. et al. Machine learning bandgaps of double perovskites. Sci. Rep. 6 , 19375 (2016).

Lu, S. et al. Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning. Nat. Commun. 9 , 3405 (2018).

Askerka, M. et al. Learning-in-templates enables accelerated discovery and synthesis of new stable double perovskites. J. Am. Chem. Soc. 141 , 3682–3690 (2019).

Jain, A. & Bligaard, T. Atomic-position independent descriptor for machine learning of material properties. Phys. Rev. B 98 , 214112 (2018).

Choubisa, H. et al. Crystal site feature embedding enables exploration of large chemical spaces. Matter 3 , 433–448 (2020).

Xie, T. & Grossman, J. C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120 , 145301–145306 (2018).

Broberg, D. et al. PyCDT: a Python toolkit for modeling point defects in semiconductors and insulators. Comput. Phys. Commun. 226 , 165–179 (2018).

Roch, L. M. et al. ChemOS: an orchestration software to democratize autonomous discovery. PLoS ONE 15 , 1–18 (2020).

Wei, L., Xu, X., Gurudayal, Bullock, J. & Ager, J. W. Machine learning optimization of p-type transparent conducting films. Chem. Mater. 31 , 7340–7350 (2019).

Schubert, M. F. et al. Design of multilayer antireflection coatings made from co-sputtered and low-refractive-index materials by genetic algorithm. Opt. Express 16 , 5290–5298 (2008).

Wang, C., Yu, S., Chen, W. & Sun, C. Highly efficient light-trapping structure design inspired by natural evolution. Sci. Rep. 3 , 1025 (2013).

Ripalda, J. M., Buencuerpo, J. & García, I. Solar cell designs by maximizing energy production based on machine learning clustering of spectral variations. Nat. Commun. 9 , 5126 (2018).

Demant, M., Virtue, P., Kovvali, A., Yu, S. X. & Rein, S. Learning quality rating of As-Cut mc-Si wafers via convolutional regression networks. IEEE J. Photovolt. 9 , 1064–1072 (2019).

Musztyfaga-Staszuk, M. & Honysz, R. Application of artificial neural networks in modeling of manufactured front metallization contact resistance for silicon solar cells. Arch. Metall. Mater. 60 , 1673–1678 (2015).

Sendek, A. D. et al. Holistic computational structure screening of more than 12000 candidates for solid lithium-ion conductor materials. Energy Environ. Sci. 10 , 306–320 (2017).

Ahmad, Z., Xie, T., Maheshwari, C., Grossman, J. C. & Viswanathan, V. Machine learning enabled computational screening of inorganic solid electrolytes for suppression of dendrite formation in lithium metal anodes. ACS Cent. Sci. 4 , 996–1006 (2018).

Zhang, Y. et al. Unsupervised discovery of solid-state lithium ion conductors. Nat. Commun. 10 , 5260 (2019).

Doan, H. A. et al. Quantum chemistry-informed active learning to accelerate the design and discovery of sustainable energy storage materials. Chem. Mater. 32 , 6338–6346 (2020).

Chemali, E., Kollmeyer, P. J., Preindl, M. & Emadi, A. State-of-charge estimation of Li-ion batteries using deep neural networks: a machine learning approach. J. Power Sources 400 , 242–255 (2018).

Richardson, R. R., Osborne, M. A. & Howey, D. A. Gaussian process regression for forecasting battery state of health. J. Power Sources 357 , 209–219 (2017).

Berecibar, M. et al. Online state of health estimation on NMC cells based on predictive analytics. J. Power Sources 320 , 239–250 (2016).

Severson, K. A. et al. Data-driven prediction of battery cycle life before capacity degradation. Nat. Energy 4 , 383–391 (2019).

Attia, P. M. et al. Closed-loop optimization of fast-charging protocols for batteries with machine learning. Nature 578 , 397–402 (2020).

Joshi, R. P. et al. Machine learning the voltage of electrode materials in metal-ion batteries. ACS Appl. Mater. Interf. 11 , 18494–18503 (2019).

Cubuk, E. D., Sendek, A. D. & Reed, E. J. Screening billions of candidates for solid lithium-ion conductors: a transfer learning approach for small data. J. Chem. Phys. 150 , 214701 (2019).

Sendek, A. D. et al. Machine learning-assisted discovery of solid Li-ion conducting materials. Chem. Mater. 31 , 342–352 (2019).

Kim, S., Jinich, A. & Aspuru-Guzik, A. MultiDK: a multiple descriptor multiple kernel approach for molecular discovery and its application to organic flow battery electrolytes. J. Chem. Inf. Model. 57 , 657–668 (2017).

Jinich, A., Sanchez-Lengeling, B., Ren, H., Harman, R. & Aspuru-Guzik, A. A mixed quantum chemistry/machine learning approach for the fast and accurate prediction of biochemical redox potentials and its large-scale application to 315000 redox reactions. ACS Cent. Sci. 5 , 1199–1210 (2019).

Sarkar, A. et al. High entropy oxides for reversible energy storage. Nat. Commun. 9 , 3400 (2018).

Choudhury, S. et al. Stabilizing polymer electrolytes in high-voltage lithium batteries. Nat. Commun. 10 , 3091 (2019).

Sanchez-Lengeling, B. & Aspuru-Guzik, A. Inverse molecular design using machine learning: generative models for matter engineering. Science 361 , 360–365 (2018).

Ng, M.-F., Zhao, J., Yan, Q., Conduit, G. J. & Seh, Z. W. Predicting the state of charge and health of batteries using data-driven machine learning. Nat. Mach. Intell. 2 , 161–170 (2020).

Steinmann, S. N. & Seh, Z. W. Understanding electrified interfaces. Nat. Rev. Mater. 6 , 289–291 (2021).

Kandasamy, N., Badrinarayanan, R., Kanamarlapudi, V., Tseng, K. & Soong, B.-H. Performance analysis of machine-learning approaches for modeling the charging/discharging profiles of stationary battery systems with non-uniform cell aging. Batteries 3 , 18 (2017).

Wei, Q., Liu, D. & Shi, G. A novel dual iterative Q-learning method for optimal battery management in smart residential environments. IEEE Trans. Ind. Electron. 62 , 2509–2518 (2015).

Murphey, Y. L. et al. Intelligent hybrid vehicle power control — Part II: online intelligent energy management. IEEE Trans. Vehicular Technol. 62 , 69–79 (2013).

Seh, Z. W. et al. Combining theory and experiment in electrocatalysis: insights into materials design. Science 355 , eaad4998 (2017).

Staffell, I. et al. The role of hydrogen and fuel cells in the global energy system. Energy Environ. Sci. 12 , 463–491 (2019).

Montoya, J. H. H. et al. Materials for solar fuels and chemicals. Nat. Mater. 16 , 70–81 (2017).

Pérez-Ramírez, J. & López, N. Strategies to break linear scaling relationships. Nat. Catal. 2 , 971–976 (2019).

Shi, C., Hansen, H. A., Lausche, A. C. & Norskov, J. K. Trends in electrochemical CO 2 reduction activity for open and close-packed metal surfaces. Phys. Chem. Chem. Phys. 16 , 4720–4727 (2014).

Calle-Vallejo, F., Loffreda, D., Koper, M. T. M. & Sautet, P. Introducing structural sensitivity into adsorption-energy scaling relations by means of coordination numbers. Nat. Chem. 7 , 403–410 (2015).

Ulissi, Z. W. et al. Machine-learning methods enable exhaustive searches for active bimetallic facets and reveal active site motifs for CO 2 reduction. ACS Catal. 7 , 6600–6608 (2017).

Nørskov, J. K., Studt, F., Abild-Pedersen, F. & Bligaard, T. Activity and selectivity maps. In Fundamental Concepts in Heterogeneous Catalysis 97–113 (John Wiley, 2014).

Garijo del Río, E., Mortensen, J. J. & Jacobsen, K. W. Local Bayesian optimizer for atomic structures. Phys. Rev. B 100 , 104103 (2019).

Jørgensen, M. S., Larsen, U. F., Jacobsen, K. W. & Hammer, B. Exploration versus exploitation in global atomistic structure optimization. J. Phys. Chem. A 122 , 1504–1509 (2018).

Jacobsen, T. L., Jørgensen, M. S. & Hammer, B. On-the-fly machine learning of atomic potential in density functional theory structure optimization. Phys. Rev. Lett. 120 , 026102 (2018).

Peterson, A. A. Acceleration of saddle-point searches with machine learning. J. Chem. Phys. 145 , 074106 (2016).

Ulissi, Z. W., Medford, A. J., Bligaard, T. & Nørskov, J. K. To address surface reaction network complexity using scaling relations machine learning and DFT calculations. Nat. Commun. 8 , 14621 (2017).

Huang, Y., Chen, Y., Cheng, T., Wang, L.-W. & Goddard, W. A. Identification of the selective sites for electrochemical reduction of CO to C 2+ products on copper nanoparticles by combining reactive force fields, density functional theory, and machine learning. ACS Energy Lett. 3 , 2983–2988 (2018).

Chen, Y., Huang, Y., Cheng, T. & Goddard, W. A. Identifying active sites for CO 2 reduction on dealloyed gold surfaces by combining machine learning with multiscale simulations. J. Am. Chem. Soc. 141 , 11651–11657 (2019).

Lai, Y., Jones, R. J. R., Wang, Y., Zhou, L. & Gregoire, J. M. Scanning electrochemical flow cell with online mass spectroscopy for accelerated screening of carbon dioxide reduction electrocatalysts. ACS Comb. Sci. 21 , 692–704 (2019).

Lai, Y. et al. The sensitivity of Cu for electrochemical carbon dioxide reduction to hydrocarbons as revealed by high throughput experiments. J. Mater. Chem. A 7 , 26785–26790 (2019).

Tran, K. & Ulissi, Z. W. Active learning across intermetallics to guide discovery of electrocatalysts for CO 2 reduction and H 2 evolution. Nat. Catal. 1 , 696–703 (2018).

Zhong, M. et al. Accelerated discovery of CO 2 electrocatalysts using active machine learning. Nature 581 , 178–183 (2020).

Tshitoyan, V. et al. Unsupervised word embeddings capture latent knowledge from materials science literature. Nature 571 , 95–98 (2019).

Yao, Y. et al. Carbothermal shock synthesis of high-entropy-alloy nanoparticles. Science 359 , 1489–1494 (2018).

Yao, Y. et al. High-throughput, combinatorial synthesis of multimetallic nanoclusters. Proc. Natl Acad. Sci. USA 117 , 6316–6322 (2020).

Timoshenko, J. & Roldan Cuenya, B. In situ/operando electrocatalyst characterization by X-ray absorption spectroscopy. Chem. Rev. 121 , 882–961 (2021).

Zheng, C., Chen, C., Chen, Y. & Ong, S. P. Random forest models for accurate identification of coordination environments from X-ray absorption near-edge structure. Patterns 1 , 100013–100023 (2020).

Torrisi, S. B. et al. Random forest machine learning models for interpretable X-ray absorption near-edge structure spectrum-property relationships. npj Comput. Mater. 6 , 109 (2020).

Timoshenko, J. et al. Neural network approach for characterizing structural transformations by X-ray absorption fine structure spectroscopy. Phys. Rev. Lett. 120 , 225502 (2018).

Marcella, N. et al. Neural network assisted analysis of bimetallic nanocatalysts using X-ray absorption near edge structure spectroscopy. Phys. Chem. Chem. Phys. 22 , 18902–18910 (2020).

Chen, K., Laghrouche, S. & Djerdir, A. Degradation model of proton exchange membrane fuel cell based on a novel hybrid method. Appl. Energy 252 , 113439–113447 (2019).

Ma, R. et al. Data-driven proton exchange membrane fuel cell degradation predication through deep learning method. Appl. Energy 231 , 102–115 (2018).

Jeppesen, C. et al. Fault detection and isolation of high temperature proton exchange membrane fuel cell stack under the influence of degradation. J. Power Sources 359 , 37–47 (2017).

Liu, J. et al. Sequence fault diagnosis for PEMFC water management subsystem using deep learning with t-SNE. IEEE Access. 7 , 92009–92019 (2019).

Ansari, M. A., Rizvi, S. M. A. & Khan, S. Optimization of electrochemical performance of a solid oxide fuel cell using artificial neural network. in 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT) 4230–4234 (IEEE, 2016).

Zhang, C. et al. Modelling of solid oxide electrolyser cell using extreme learning machine. Electrochim. Acta 251 , 137–144 (2017).

Esche, E., Weigert, J., Budiarto, T., Hoffmann, C. & Repke, J.-U. Optimization under uncertainty based on a data-driven model for a chloralkali electrolyzer cell. Computer-aided Chem. Eng. 46 , 577–582 (2019).

Siddaiah, R. & Saini, R. P. A review on planning, configurations, modeling and optimization techniques of hybrid renewable energy systems for off grid applications. Renew. Sustain. Energy Rev. 58 , 376–396 (2016).

Yin, L., Yu, T., Zhang, X. & Yang, B. Relaxed deep learning for real-time economic generation dispatch and control with unified time scale. Energy 149 , 11–23 (2018).

Yu, T., Wang, H. Z., Zhou, B., Chan, K. W. & Tang, J. Multi-agent correlated equilibrium Q ( λ ) learning for coordinated smart generation control of interconnected power grids. IEEE Trans. Power Syst. 30 , 1669–1679 (2015).

Marino, D. L., Amarasinghe, K. & Manic, M. Building energy load forecasting using deep neural networks. in IECON Proceedings (Industrial Electronics Conference) 7046–7051 (IECON, 2016).

Ryu, S., Noh, J. & Kim, H. Deep neural network based demand side short term load forecasting. in 2016 IEEE International Conference on Smart Grid Communications (SmartGridComm 2016) 308–313 (IEEE, 2016).

Mocanu, E., Nguyen, P. H., Kling, W. L. & Gibescu, M. Unsupervised energy prediction in a Smart Grid context using reinforcement cross-building transfer learning. Energy Build. 116 , 646–655 (2016).

Lund, P. D., Lindgren, J., Mikkola, J. & Salpakari, J. Review of energy system flexibility measures to enable high levels of variable renewable electricity. Renew. Sustain. Energy Rev. 45 , 785–807 (2015).

Kim, B. G., Zhang, Y., Van Der Schaar, M. & Lee, J. W. Dynamic pricing and energy consumption scheduling with reinforcement learning. IEEE Trans. Smart Grid 7 , 2187–2198 (2016).

Dusparic, I., Taylor, A., Marinescu, A., Cahill, V. & Clarke, S. Maximizing renewable energy use with decentralized residential demand response. in 2015 IEEE 1st International Smart Cities Conference (ISC2 2015 ) 1–6 (IEEE, 2015).

Dusparic, I., Harris, C., Marinescu, A., Cahill, V. & Clarke, S. Multi-agent residential demand response based on load forecasting. in 2013 1st IEEE Conference on Technologies for Sustainability (SusTech 2013) 90–96 (IEEE, 2013).

Bengio, Y., Courville, A. & Vincent, P. Representation learning: a review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence 35 , 1798–1828 (2013).

Duvenaud, D. et al. Convolutional networks on graphs for learning molecular fingerprints. in Advances In Neural Information Processing Systems 2224–2232 (NIPS, 2015).

Gómez-Bombarelli, R. et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4 , 268–276 (2018).

Krenn, M., Hase, F., Nigam, A., Friederich, P. & Aspuru-Guzik, A. Self-referencing embedded strings (SELFIES): a 100% robust molecular string representation. Mach. Learn. Sci. Technol. 1 , 045024–045031 (2020).

Jin, W., Barzilay, R. & Jaakkola, T. Junction tree variational autoencoder for molecular graph generation. Mach. Learn. 5 , 3632–3648 (2018).

You, J., Liu, B., Ying, R., Pande, V. & Leskovec, J. Graph convolutional policy network for goal-directed molecular graph generation. Adv. Neural Inf. Process. Syst. 31 , 6412–6422 (2018).

Liu, Q., Allamanis, M., Brockschmidt, M. & Gaunt, A. L. Constrained graph variational autoencoders for molecule design. in Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS’18) 7806–7815 (Curran Associates Inc., 2018).

Bartók, A. P., Kondor, R. & Csányi, G. On representing chemical environments. Phys. Rev. B 87 , 184115 (2013).

Ward, L. et al. Including crystal structure attributes in machine learning models of formation energies via Voronoi tessellations. Phys. Rev. B 96 , 024104 (2017).

Isayev, O. et al. Universal fragment descriptors for predicting properties of inorganic crystals. Nat. Commun. 8 , 15679 (2017).

Ziletti, A., Kumar, D., Scheffler, M. & Ghiringhelli, L. M. Insightful classification of crystal structures using deep learning. Nat. Commun. 9 , 2775 (2018).

Ryan, K., Lengyel, J. & Shatruk, M. Crystal structure prediction via deep learning. J. Am. Chem. Soc. 140 , 10158–10168 (2018).

Park, C. W. & Wolverton, C. Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery. Phys. Rev. Mater. 4 , 063801 (2020).

Liu, X. et al. Self-Supervised Learning: Generative or Contrastive (IEEE, 2020).

Ruder, S. An overview of multi-task learning in deep neural networks. Preprint at https://doi.org/10.48550/arXiv.1706.05098 (2017).

Hospedales, T., Antoniou, A., Micaelli, P. & Storkey, A. Meta-learning in neural networks: a survey. IEEE Transactions on Pattern Analysis & Machine Intelligence 44 , 5149–5169 (2020).

Vaswani, A. et al. Attention is all you need. in Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17) 6000–6010 (Curran Associates Inc., 2017).

Veličković, P. et al. Graph attention networks. Preprint at https://doi.org/10.48550/arXiv.1710.10903 (2017).

Battaglia, P. W. et al. Relational inductive biases, deep learning, and graph networks. Preprint at https://doi.org/10.48550/arXiv.1806.01261 (2018).

Satorras, V. G., Hoogeboom, E. & Welling, M. E(n) equivariant graph neural networks. Preprint at https://doi.org/10.48550/arXiv.2102.09844 (2021).

Jain, A. et al. Commentary: The Materials Project: a materials genome approach to accelerating materials innovation. Apl. Mater. 1 , 011002–011012 (2013).

Laasner, R. et al. MatD3: a database and online presentation package for research data supporting materials discovery, design, and dissemination. J. Open Source Softw. 5 , 1945–1947 (2020).

Coley, C. W. et al. A robotic platform for flow synthesis of organic compounds informed by AI planning. Science 365 , 557 (2019).

Hachmann, J. et al. The harvard clean energy project: large-scale computational screening and design of organic photovoltaics on the world community grid. J. Phys. Chem. Lett. 2 , 2241–2251 (2011).

Bıyık, E., Wang, K., Anari, N. & Sadigh, D. Batch active learning using determinantal point processes. Preprint at https://doi.org/10.48550/arXiv.1906.07975 (2019).

Hoffmann, J. et al. Machine learning in a data-limited regime: augmenting experiments with synthetic data uncovers order in crumpled sheets. Sci. Adv. 5 , eaau6792 (2019).

Liu, J. Z. et al. Simple and principled uncertainty estimation with deterministic deep learning via distance awareness. Adv. Neural Inf. Process Syst. 33 , 7498–7512 (2020).

Lakshminarayanan, B., Pritzel, A. & Blundell, C. Simple and scalable predictive uncertainty estimation using deep ensembles. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17) 6405–6416 (Curran Associates Inc., 2017).

D’Amour, A. et al. Underspecification presents challenges for credibility in modern machine learning. Preprint at https://doi.org/10.48550/arXiv.2011.03395 (2020).

Barredo Arrieta, A. et al. Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion. 58 , 82–115 (2020).

Ribeiro, M. T., Singh, S. & Guestrin, C. “Why should I trust you?” Explaining the predictions of any classifier. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 1135–1144 (2016).

Lundberg, S. & Lee, S.-I. An unexpected unity among methods for interpreting model predictions. Preprint at https://arxiv.org/abs/1611.07478 (2016).

Bach, S. et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10 , e0130140 (2015).

Sun, W. et al. The thermodynamic scale of inorganic crystalline metastability. Sci. Adv. 2 , e1600225 (2016).

Aykol, M., Dwaraknath, S. S., Sun, W. & Persson, K. A. Thermodynamic limit for synthesis of metastable inorganic materials. Sci. Adv. 4 , eaaq0148 (2018).

Wei, J. N., Duvenaud, D. & Aspuru-Guzik, A. Neural networks for the prediction of organic chemistry reactions. ACS Cent. Sci. 2 , 725–732 (2016).

Coley, C. W. et al. A graph-convolutional neural network model for the prediction of chemical reactivity. Chem. Sci. 10 , 370–377 (2019).

Nagabhushana, G. P., Shivaramaiah, R. & Navrotsky, A. Direct calorimetric verification of thermodynamic instability of lead halide hybrid perovskites. Proc. Natl Acad. Sci. USA 113 , 7717–7721 (2016).

Sanna, S. et al. Enhancement of the chemical stability in confined δ-Bi 2 O 3 . Nat. Mater. 14 , 500–504 (2015).

Podolyan, Y., Walters, M. A. & Karypis, G. Assessing synthetic accessibility of chemical compounds using machine learning methods. J. Chem. Inf. Model. 50 , 979–991 (2010).

Coley, C. W., Rogers, L., Green, W. H. & Jensen, K. F. SCScore: synthetic complexity learned from a reaction corpus. J. Chem. Inf. Model. 58 , 252–261 (2018).

Kim, E. et al. Inorganic materials synthesis planning with literature-trained neural networks. J. Chem. Inf. Model. 60 , 1194–1201 (2020).

Huo, H. et al. Semi-supervised machine-learning classification of materials synthesis procedures. npj Comput. Mater. 5 , 62 (2019).

Tian, C., Lin, F. & Doeff, M. M. Electrochemical characteristics of layered transition metal oxide cathode materials for lithium ion batteries: surface, bulk behavior, and thermal properties. Acc. Chem. Res. 51 , 89–96 (2018).

Guilminot, E., Corcella, A., Charlot, F., Maillard, F. & Chatenet, M. Detection of Pt z + ions and Pt nanoparticles inside the membrane of a used PEMFC. J. Electrochem. Soc. 154 , B96 (2007).

Pender, J. P. et al. Electrode degradation in lithium-ion batteries. ACS Nano 14 , 1243–1295 (2020).

Li, Y. et al. Atomic structure of sensitive battery materials and interfaces revealed by cryo-electron microscopy. Science 358 , 506–510 (2017).

Wang, H. Numerical modeling of non-planar hydraulic fracture propagation in brittle and ductile rocks using XFEM with cohesive zone method. J. Pet. Sci. Eng. 135 , 127–140 (2015).

Hsu, Y.-C., Yu, C.-H. & Buehler, M. J. Using deep learning to predict fracture patterns in crystalline solids. Matter 3 , 197–211 (2020).

Wuest, T., Weimer, D., Irgens, C. & Thoben, K. D. Machine learning in manufacturing: advantages, challenges, and applications. Prod. Manuf. Res. 4 , 23–45 (2016).

De Jong, P., Sánchez, A. S., Esquerre, K., Kalid, R. A. & Torres, E. A. Solar and wind energy production in relation to the electricity load curve and hydroelectricity in the northeast region of Brazil. Renew. Sustain. Energy Rev. 23 , 526–535 (2013).

Zolfani, S. H. & Saparauskas, J. New application of SWARA method in prioritizing sustainability assessment indicators of energy system. Eng. Econ. 24 , 408–414 (2013).

Tao, F., Zhang, M., Liu, Y. & Nee, A. Y. C. Digital twin driven prognostics and health management for complex equipment. CIRP Ann. 67 , 169–172 (2018).

Yun, S., Park, J. H. & Kim, W. T. Data-centric middleware based digital twin platform for dependable cyber-physical systems. in International Conference on Ubiquitous and Future Networks (ICUFN) 922–926 (2017).

Boretti, A. Integration of solar thermal and photovoltaic, wind, and battery energy storage through AI in NEOM city. Energy AI 3 , 100038–100045 (2021).

Ghoddusi, H., Creamer, G. G. & Rafizadeh, N. Machine learning in energy economics and finance: a review. Energy Econ. 81 , 709–727 (2019).

Asensio, O. I., Mi, X. & Dharur, S. Using machine learning techniques to aid environmental policy analysis: a teaching case regarding big data and electric vehicle charging infrastructure. Case Stud. Environ. 4 , 961302 (2020).

Zheng, S., Trott, A., Srinivasa, S., Parkes, D. C. & Socher, R. The AI economist: taxation policy design via two-level deep multiagent reinforcement learning. Sci. Adv. 8 , eabk2607 (2022).

Sun, S. et al. A data fusion approach to optimize compositional stability of halide perovskites. Matter 4 , 1305–1322 (2021).

Sun, W. et al. Machine learning — assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials. Sci. Adv. 5 , eaay4275 (2019).

Sun, S. et al. Accelerated development of perovskite-inspired materials via high-throughput synthesis and machine-learning diagnosis. Joule 3 , 1437–1451 (2019).

Kirman, J. et al. Machine-learning-accelerated perovskite crystallization. Matter 2 , 938–947 (2020).

Langner, S. et al. Beyond ternary OPV: high-throughput experimentation and self-driving laboratories optimize multicomponent systems. Adv. Mater. 32 , 1907801 (2020).

Hartono, N. T. P. et al. How machine learning can help select capping layers to suppress perovskite degradation. Nat. Commun. 11 , 4172 (2020).

Odabaşı, Ç. & Yıldırım, R. Performance analysis of perovskite solar cells in 2013–2018 using machine-learning tools. Nano Energy 56 , 770–791 (2019).

Fenning, D. P. et al. Darwin at high temperature: advancing solar cell material design using defect kinetics simulations and evolutionary optimization. Adv. Energy Mater. 4 , 1400459 (2014).

Allam, O., Cho, B. W., Kim, K. C. & Jang, S. S. Application of DFT-based machine learning for developing molecular electrode materials in Li-ion batteries. RSC Adv. 8 , 39414–39420 (2018).

Okamoto, Y. & Kubo, Y. Ab initio calculations of the redox potentials of additives for lithium-ion batteries and their prediction through machine learning. ACS Omega 3 , 7868–7874 (2018).

Takagishi, Y., Yamanaka, T. & Yamaue, T. Machine learning approaches for designing mesoscale structure of Li-ion battery electrodes. Batteries 5 , 54 (2019).

Tan, Y., Liu, W. & Qiu, Q. Adaptive power management using reinforcement learning. in IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers (ICCAD ) 461–467 (IEEE, 2009).

Ermon, S., Xue, Y., Gomes, C. & Selman, B. Learning policies for battery usage optimization in electric vehicles. Mach. Learn. 92 , 177–194 (2013).

Schmidt, J., Marques, M. R. G., Botti, S. & Marques, M. A. L. Recent advances and applications of machine learning in solid-state materials science. npj Comput. Mater. 5 , 83 (2019).

Pilania, G. Machine learning in materials science: from explainable predictions to autonomous design. Comput. Mater. Sci. 193 , 110360 (2021).

Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O. & Walsh, A. Machine learning for molecular and materials science. Nature 559 , 547–555 (2018).

Kaufmann, K. et al. Crystal symmetry determination in electron diffraction using machine learning. Science 367 , 564–568 (2020).

Chen, C., Zuo, Y., Ye, W., Li, X. & Ong, S. P. Learning properties of ordered and disordered materials from multi-fidelity data. Nat. Comput. Sci. 1 , 46–53 (2021).

Liu, M., Yan, K., Oztekin, B. & Ji, S. GraphEBM: molecular graph generation with energy-based models. Preprint at https://doi.org/10.48550/arXiv.2102.00546 (2021).

Segler, M. H. S., Preuss, M. & Waller, M. P. Planning chemical syntheses with deep neural networks and symbolic AI. Nature 555 , 604–610 (2018).

Granda, J. M., Donina, L., Dragone, V., Long, D.-L. & Cronin, L. Controlling an organic synthesis robot with machine learning to search for new reactivity. Nature 559 , 377–381 (2018).

Epps, R. W. et al. Artificial chemist: an autonomous quantum dot synthesis bot. Adv. Mater. 32 , 2001626 (2020).

MacLeod, B. P. et al. Self-driving laboratory for accelerated discovery of thin-film materials. Sci. Adv. 6 , eaaz8867 (2020).

Li, Z. et al. Robot-accelerated perovskite investigation and discovery. Chem. Mater. 32 , 5650–5663 (2020).

Aguiar, J. A., Gong, M. L., Unocic, R. R., Tasdizen, T. & Miller, B. D. Decoding crystallography from high-resolution electron imaging and diffraction datasets with deep learning. Sci. Adv. 5 , eaaw1949 (2019).

Download references

Acknowledgements

Z.Y. and A.A.-G. were supported as part of the Nanoporous Materials Genome Center by the US Department of Energy, Office of Science, Office of Basic Energy Sciences under award number DE-FG02-17ER16362 and the US Department of Energy, Office of Science — Chicago under award number DE-SC0019300. A.J. was financially supported by Huawei Technologies Canada and the Natural Sciences and Engineering Research Council (NSERC). L.M.M.-M. thanks the support of the Defense Advanced Research Projects Agency under the Accelerated Molecular Discovery Program under cooperative agreement number HR00111920027 dated 1 August 2019. Y.W. acknowledges funding support from the Singapore National Research Foundation under its Green Buildings Innovation Cluster (GBIC award number NRF2015ENC-GBICRD001-012) administered by the Building and Construction Authority, its Green Data Centre Research (GDCR award number NRF2015ENC-GDCR01001-003) administered by the Info-communications Media Development Authority, and its Energy Programme (EP award number NRF2017EWT-EP003-023) administered by the Energy Market Authority of Singapore. A.A.-G. is a Canadian Institute for Advanced Research (CIFAR) Lebovic Fellow. E.H.S. acknowledges funding by the Ontario Ministry of Colleges and Universities (grant ORF-RE08-034), the Natural Sciences and Engineering Research Council (NSERC) of Canada (grant RGPIN-2017-06477), the Canadian Institute for Advanced Research (CIFAR) (grant FS20-154 APPT.2378) and the University of Toronto Connaught Fund (grant GC 2012-13). Z.W.S. acknowledges funding by the Singapore National Research Foundation (NRF-NRFF2017-04).

Author information

These authors contributed equally: Zhenpeng Yao, Yanwei Lum, Andrew Johnston.

Authors and Affiliations

Shanghai Key Laboratory of Hydrogen Science & Center of Hydrogen Science, School of Materials Science and Engineering, Shanghai Jiao Tong University, Shanghai, China

Zhenpeng Yao

Chemical Physics Theory Group, Department of Chemistry and Department of Computer Science, University of Toronto, Toronto, Ontario, Canada

Zhenpeng Yao, Luis Martin Mejia-Mendoza & Alán Aspuru-Guzik

Innovation Center for Future Materials, Zhangjiang Institute for Advanced Study, Shanghai Jiao Tong University, Shanghai, China

State Key Laboratory of Metal Matrix Composites, School of Materials Science and Engineering, Shanghai Jiao Tong University, Shanghai, China

Institute of Materials Research and Engineering, Agency for Science, Technology and Research (A*STAR), Innovis, Singapore, Singapore

Yanwei Lum & Zhi Wei Seh

Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario, Canada

Yanwei Lum, Andrew Johnston & Edward H. Sargent

School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore

Xin Zhou & Yonggang Wen

Vector Institute for Artificial Intelligence, Toronto, Ontario, Canada

• Alán Aspuru-Guzik

You can also search for this author in PubMed   Google Scholar

Contributions

Z.Y., Y.L. and A.J. contributed equally to this work. All authors contributed to the writing and editing of the manuscript.

Corresponding authors

Correspondence to Alán Aspuru-Guzik , Edward H. Sargent or Zhi Wei Seh .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Peer review

Peer review information.

Nature Reviews Materials thanks Shijing Sun and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Related links

MatD3 database: https://github.com/HybriD3-database/MatD3

Materials Project: https://materialsproject.org/

Machine learning techniques that can query a user interactively to modify its current strategy (that is, label an input).

(AI). Theory and development of computer systems that exhibit intelligence.

A system for adjusting the power output of multiple generators at different power plants, in response to changes in the load.

A technology development pipeline that incorporates automation to go from idea to realization of technology. ‘Closed’ refers to the concept that the system improves with experience and iterations.

Process of increasing the amount of data through adding slightly modified copies or newly created synthetic data from existing data.

A generative graphical model, or alternatively a class of deep neural network, composed of multiple layers of latent variables, with connections between the layers but not between units within each layer.

(DL). Machine learning subfield that is based on neural networks with representation learning.

The ability to adapt to new, unseen data, drawn from the same distribution as the one used to create the model.

Machine learning techniques that learn to model the data distribution of a dataset and sample new data points.

Degree to which a human can understand a model’s decision. Interpretability can be used to build trust and credibility.

A design method where new materials and compounds are ‘reverse-engineered’ simply by inputting a set of desired properties and characteristics and then using an optimization algorithm to generate a predicted solution.

A special kind of recurrent neural networks that are capable of selectively remembering patterns for a long duration of time.

(ML). Field within artificial intelligence that deals with learning algorithms, which improve automatically through experience (data).

A computerized system composed of multiple interacting intelligent agents.

The combination of ridge regression (a method of estimating the coefficients of multiple-regression models in scenarios where the independent variables are highly correlated) with multiple kernel techniques.

Models that involve the analysis of multiple, simultaneous physical phenomena, which can include heat transfer, fluid flow, deformation, electromagnetics, acoustics and mass transport.

The field of solving problems that have important features at multiple scales of time and/or space.

A neural network is composed of parameterized and optimizable transformations.

A class of artificial neural networks where connections between nodes form a directed or undirected graph along a temporal sequence.

Process of incorporating additional information into the model to constrain its solution space.

Machine learning techniques that make a sequence of decisions to maximize a reward.

Features used in a representation learning model, which transforms inputs into new features for a task.

Technique for solving problems in the planning of chemical synthesis.

A robotic equipment automated chemical synthesis plan.

Design process composed of several stages where materials are iteratively filtered and ranked to arrive to a few top candidates.

Machine learning techniques that involve the usage of labelled data.

Machine learning techniques that adapt a learned representation or strategy from one dataset to another.

Process of evaluating the statistical confidence of model.

Machine learning techniques that learn patterns from unlabelled data.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Cite this article.

Yao, Z., Lum, Y., Johnston, A. et al. Machine learning for a sustainable energy future. Nat Rev Mater 8 , 202–215 (2023). https://doi.org/10.1038/s41578-022-00490-5

Download citation

Accepted : 14 September 2022

Published : 18 October 2022

Issue Date : March 2023

DOI : https://doi.org/10.1038/s41578-022-00490-5

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

This article is cited by

Artificial intelligence-based methods for renewable power system operation.

• Yuanzheng Li
• Yizhou Ding
• Zhigang Zeng

Nature Reviews Electrical Engineering (2024)

Nature-inspired interfacial engineering for energy harvesting

• Baoping Zhang
• Wanghuai Xu
• Zuankai Wang

Attention towards chemistry agnostic and explainable battery lifetime prediction

• Fuzhan Rahmanian
• Robert M. Lee
• Helge Sören Stein

npj Computational Materials (2024)

Bringing digital synthesis to Mars

• Mark D. Symes
• Leroy Cronin

Nature Synthesis (2024)

Accelerating discovery in organic redox flow batteries

Nature Computational Science (2024)

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

energy management Recently Published Documents

Total documents.

• Latest Documents
• Most Cited Documents
• Contributed Authors
• Related Sources
• Related Keywords

Coordinated energy management for an islanded microgrid with multi-energy and multi-storage units

Developing optimal energy management of integrated energy systems in the hybrid electricity and gas networks, optimal energy management of micro-grid using sparrow search algorithm, critical review on structural architecture, energy control strategies and development process towards optimal energy management in hybrid vehicles, efficient solution of many-objective home energy management systems, optimal energy management system for microgrids considering energy storage, demand response and renewable power generation, comparison of online and offline deep reinforcement learning with model predictive control for thermal energy management, microgrid energy management system for smart home using multi-agent system.

This paper proposes a multi-agent system for energy management in a microgrid for smart home applications, the microgrid comprises a photovoltaic source, battery energy storage, electrical loads, and an energy management system (EMS) based on smart agents. The microgrid can be connected to the grid or operating in island mode. All distributed sources are implemented using MATLAB/Simulink to simulate a dynamic model of each electrical component. The agent proposed can interact with each other to find the best strategy for energy management using the java agent development framework (JADE) simulator. Furthermore, the proposed agent framework is also validated through a different case study, the efficiency of the proposed approach to schedule local resources and energy management for microgrid is analyzed. The simulation results verify the efficacy of the proposed approach using Simulink/JADE co-simulation.

Energy management of Internet data centers in multiple local energy markets

Research on energy management strategy of fuel cell–battery–supercapacitor passenger vehicle, export citation format, share document.

Create an account

Create a free IEA account to download our reports or subcribe to a paid service.

Case Study: Artificial Intelligence for Building Energy Management Systems

Commercial buildings account for a significant share of global energy consumption. Yet in many commercial buildings, energy is wasted – for example, by providing energy services when buildings are unoccupied. This problem arises because commercial buildings are large, complex systems housing diverse occupants with varying behaviours and needs.

As building energy management systems (BMSs) have to cater to a range of user behaviour, building energy use is not always optimised. Now, as data on building energy use has increased, a wide variety of information is available to optimise BMSs so that they deliver energy services exactly when they are needed.

Concurrently, intermittent sources of renewable energy have grown significantly, creating challenges for grid operators tasked with supplying a steady supply of electricity to the grid. In this environment, matching supply and demand is crucial, and while storage technologies are one solution, tapping into sources of flexible demand is another.

Commercial buildings have the potential to participate in energy markets as sources of flexible demand, reducing their load when required and increasing it when supplies of electricity are plentiful, without having any impact on their operational performance. Doing so would allow building owners to generate additional revenue streams from buyers of their flexible load. However, this requires sophisticated BMSs that allow the building to participate in electricity markets in real-time, and make predictions on energy supply and demand, to ensure that building occupants are largely oblivious to changes in building energy use.

Description

Tapping into the plentiful data that exists to optimise commercial building energy use and allow commercial buildings to participate in markets for flexible demand is now being made possible thanks to machine-based artificial intelligence algorithms.

One of these systems is called “Flex2X”, developed by UK-based company Grid Edge. The system works by combining data obtained from a building’s existing energy management system with other data sources (for example, on weather conditions) and analysing it using artificial intelligence algorithms that can optimise the building’s energy use in real time. The algorithms are considered “artificially intelligent” because they change based on the data they receive, a process referred to as “learning”. This allows the software to make predictions for the building’s energy use, 24 hours in advance, based on its experiences in the past.

The software is also connected to the electricity meter and the wider electricity network. This allows it to monitor the price and generation mix of electricity, and decide when to increase or decrease the electricity load of the building, based on the cost or carbon-intensity of electricity at any given time.

By controlling when the building uses more or less energy, the software converts the building’s electricity load profile from being more or less a fixed load, into a flexible load. Flexible loads are a valuable commodity in today’s energy markets because they help energy market operators to better manage peaks and troughs in demand, and incorporate more intermittent renewable energy sources into the grid.

Grid Edge’s role in the energy system 1

This technology could potentially realise a number of benefits for a range of parties.

For building occupants, increasing the intelligence of the building management system should ensure that comfort is optimised and energy services are available when needed while energy costs are reduced thanks to reduced wastage. In addition, occupants interested in questions such as the sustainability of their building’s operations would have access to real-time data on information such as the carbon-intensity of the building’s energy supply.

For building owners/operators, intelligent building management systems like Grid Edge offer the opportunity to reduce costs, cut carbon and maximise comfort through load-shifting and optimisation, as well as recoup the cost of upgrading the building, by selling the building’s flexible load on the market. This could translate to a greater willingness to invest in sustainability upgrades, knowing that the upfront costs of such upgrades could be offset through trading the building’s flexible load.

For grid operators, this technology promises to unlock new, predictable sources of flexible demand, which will help in balancing supply and demand, especially useful as the share of intermittent renewable sources of energy increases.

Measured benefits include:

• Cost savings and revenue generation equivalent to >10% of annual on-site energy costs; • Carbon reduction through load-shifting and efficiency measures (up to 40% has been evidenced).

Opportunities

Grid Edge has deployed its technology with early-adopter customers throughout the UK and is actively developing partnerships with global energy and building controls companies to scale their technology.

In relation to the energy demand optimisation aspect of the technology, the key barriers are likely to be mistrust by building owners and occupants that the technology can deliver reductions in energy consumption without compromising energy services and comfort.

In relation to the flexible load aspect of the technology, barriers are likely to be regulatory. Energy markets rules must permit the trading of flexible demand at a scale that allows commercial buildings to participate in the market. For example, in some energy markets, the minimum allowable bids for participating are higher than the size of flexible loads likely to be offered by commercial buildings. In addition, some energy markets require access fees for participation, which might pose a barrier to entry for small-scale participants.

Scott, J, Grid Edge: Artificial Intelligence for Energy Systems, Presentation delivered at International Energy Agency Workshop on Modernising Energy Efficiency through Digitalisation, Paris, 27 March 2019

Reference 1

Energy efficiency and digitalisation.

Energy efficiency is changing, with new digital technologies enabling greater control, optimisation and analytics

A new era of shared clean energy leadership begins in China

The success of wind and solar is powered by strong policy support

The future is brightness as a service

Subscription successful

Thank you for subscribing. You can unsubscribe at any time by clicking the link at the bottom of any IEA newsletter.

Intelligent Demand Side Management for Residential Consumer Comprise of Electric Vehicle, Energy Storage System and Renewable Energy Source

• ORIGINAL CONTRIBUTION
• Published: 16 May 2024

Cite this article

• C. Kishor Muley   ORCID: orcid.org/0009-0002-4629-3542 1 &
• Sandeep Bhongade 1  

22 Accesses

Explore all metrics

The existing energy grid heavily relies on demand-side management. The Demand response, load management strategies, and demand side management are helpful to a utility for the reduction of peak load, and the end user of electricity benefits from the incentives for being a part of the demand response program. The work discussed in this paper is primarily focused on the control of consumer side load, for the reduction in total cost of consumption. The proposed energy management techniques claim to reduce the consumption of energy cost over a day to an appreciable level. It has given complete independence to the consumer for opting for the control strategy as per his comfort and aim of cost reduction. By using the suggested approaches, the bilateral power flow reduces the overall load demand and settles the new load curve near the average load line. About intelligent homes, two distinct scenarios are proposed, residence with EV and ESS and secondly, incorporating EV, ESS, and PV. The MATLAB simulation is carried out for the proposed control method, which shows considerably reduced costs on electricity bills over a whole day. Apart from that, the outcomes of the suggested system for energy control are contrasted with earlier research published in the literature, which found superior outcomes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Similar content being viewed by others

Strategies to save energy in the context of the energy crisis: a review

Electric Vehicles Charging Technology Review and Optimal Size Estimation

Battery Technologies for Grid-Level Large-Scale Electrical Energy Storage

S.L. Arun, M. Selvan, Smart residential energy management system for demand response in buildings with energy storage devices. Front. Energy (2018). https://doi.org/10.1007/s11708-018-0538-2

Article   Google Scholar  

L. Chandra, S. Chanana, Energy management of smart homes with energy storage, rooftop Pv and electric vehicle. In: IEEE international students' conference on electrical, electronics and computer science (SCEECS), Bhopal, India pp. 1–6, (2018)

A.M. Jasim, B.H. Jasim, A. Flah, V. Bolshev, L. Mihet-Popa, A new optimized demand management system for smart grid-based residential buildings adopting renewable and storage energies. Energy Rep. 9 , 4018–4035 (2023)

N.T. Mbungu, R.M. Naidoo, R.C. Bansal, M.W. Siti, D.H. Tungadio, An overview of renewable energy resources and grid integration for commercial building applications. J. Energy Storage (2020). https://doi.org/10.1016/j.est.2020.101385

A.K. Candan, A.R. Boynuegri, N. Onat, Home energy management system for enhancing grid resiliency in post-disaster recovery period using electric vehicle. Sustain. Energy, Grids Netw. (2023). https://doi.org/10.1016/j.segan.2023.101015

B. Han, Y. Zahraoui, M. Mubin, S. Mekhilef, M. Seyedmahmoudian, A. Stojcevski, Home energy management systems: a review of the concept, architecture, and scheduling strategies. IEEE Access 11 , 19999–20025 (2023)

S. Khemakhem, M. Rekik, L. Krichen, Double layer home energy supervision strategies based on demand response and plug-in electric vehicle control for flattening power load curves in a smart grid. Energy 167 , 312–324 (2019)

X. Wu, X. Hu, X. Yin, S.J. Moura, Stochastic Optimal Energy Management of Smart Home with PEV Energy Storage. IEEE Trans. Smart Grid 9 (3), 2065–2075 (2018)

U. Datta, A. Kalam, J. Shi, Electric vehicle (EV) in home energy management to reduce daily electricity costs of residential customer. J. Sci. Industr. Res. 77 (10), 559–565 (2018)

Google Scholar  

M.A.A. Abdalla, W. Min, O.A.A. Mohammed, Two-Stage Energy Management Strategy of EV and PV Integrated Smart Home to Minimize Electricity Cost and Flatten Power Load Profile. Energies (2020). https://doi.org/10.3390/en13236387

N. Misljenovic, M. Znidarec, G. Knezevic, D. Sljivac, A. Sumper, A Review of Energy Management Systems and Organizational Structures of Prosumers. Energies (2023). https://doi.org/10.3390/en16073179

D.M. Minhas, J. Meiers, G. Frey, Electric vehicle battery storage concentric intelligent home energy management system using real-life data sets. Energies (2022). https://doi.org/10.3390/en15051619

O. Ayan, B. Turkey Domestic electrical load management in smart grids and classification of residential loads. In: 2018 5th International conference on electrical and electronic engineering (ICEEE), Istanbul, Turkey, pp. 279–283 (2018)

R. Khezri, A. Mahmoudi, M.H. Haque, A demand side management approach for optimal sizing of standalone renewable-battery systems. IEEE Trans. Sustain. Energy 12 (4), 2184–2194 (2021)

Q. Yu, Y. Liu, X. Han, S. Dong, Z. Jiang, L. Li, Y. Zhang, D. Wang, Research of Control Strategy of Storage Energy in Hybrid Integrated Energy Stations. In: 2021 IEEE 4th International conference on electronics technology (ICET), Chengdu, China, pp. 1347–1351 (2021)

M. Wang, M.A.A. Abdalla, Optimal energy scheduling based on jaya algorithm for integration of vehicle-to-home and energy storage system with photovoltaic generation in smart home. Sensors 22 (4), 1–23 (2022)

O. Almughram, B.A. Zafar, A reinforcement learning approach for integrating an intelligent home energy management system with a vehicle-to-home unit. Appl. Sci. (2023). https://doi.org/10.3390/app13095539

X. Wu, X. Hu, Y. Teng, S. Qian, R. Cheng, Optimal integration of a hybrid solar-battery power source into smart home nanogrid with plug-in electric vehicle. J. Power Sour. 363 , 277–283 (2017)

A.O. Ali, M.R. Elmarghany, M.M. Abdelsalam, M.N. Sabry, A.M. Hamed, Closed-loop home energy management system with Renewable energy sources in a smart grid: a comprehensive review. J. Energy Storage (2022). https://doi.org/10.1016/j.est.2022.104609

A. Chakir, M. Abid, M. Tabaa, H. Hachimi, Demand-side management strategy in a smart home using electric vehicle and hybrid renewable energy system. Energy Rep. 8 , 383–393 (2022)

M. Alilou, B. Tousi, H. Shayeghi, Home energy management in a residential smart microgrid under stochastic penetration of solar panels and electric vehicles. Sol. Energy 212 , 6–18 (2020)

A. Sangswang, M. Konghirun, Optimal strategies in home energy management system integrating solar power, energy storage, and vehicle-to-grid for grid support and energy efficiency. IEEE Trans. Industr. Appl. 56 (5), 5716–5728 (2020)

S. Bhongade, R.S. Dawar, S.L. Sisodiya, Demand-side management in an indian village. J. Inst. Eng. India Ser. B 103 , 63–71 (2022)

M. Wang, M.A.A. Abdalla, Optimal energy scheduling based on jaya algorithm for integration of vehicle-to-home and energy storage system with photovoltaic generation in smart home. Sensors 22 (4), 1306 (2022)

P. Kumar, N. Malik, A. Garg, Comparative analysis of solar-battery storage sizing in net metering and zero export systems. Energy Sustain. Dev. 69 , 41–50 (2022)

Download references

The authors have not disclosed any funding.

Author information

Authors and affiliations.

Department of Electrical Engineering, Shri Govindram Seksaria Institute of Technology and Science, Indore, Madhya Pradesh, India

C. Kishor Muley & Sandeep Bhongade

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to C. Kishor Muley .

Ethics declarations

Conflict of interest.

The authors have not disclosed any competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Muley, C.K., Bhongade, S. Intelligent Demand Side Management for Residential Consumer Comprise of Electric Vehicle, Energy Storage System and Renewable Energy Source. J. Inst. Eng. India Ser. B (2024). https://doi.org/10.1007/s40031-024-01071-6

Download citation

Received : 07 July 2023

Accepted : 29 April 2024

Published : 16 May 2024

DOI : https://doi.org/10.1007/s40031-024-01071-6

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Demand side management
• Energy management techniques
• Electric vehicle
• Energy storage system
• Renewable energy source
• Find a journal
• Publish with us
• Track your research

Building Energy Management System: An Overview of Recent Literature Research

Ieee account.

• Change Username/Password
• Update Address

Purchase Details

• Payment Options
• Order History
• View Purchased Documents

Profile Information

• Communications Preferences
• Profession and Education
• Technical Interests
• US & Canada: +1 800 678 4333
• Worldwide: +1 732 981 0060
• Contact & Support
• About IEEE Xplore
• Accessibility
• Terms of Use
• Nondiscrimination Policy
• Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

AI Is Everybody’s Business

This briefing presents three principles to guide business leaders when making AI investments: invest in practices that build capabilities required for AI, involve all your people in your AI journey, and focus on realizing value from your AI projects. The principles are supported by the MIT CISR data monetization research, and the briefing illustrates them using examples from the Australia Taxation Office and CarMax. The three principles apply to any kind of AI, defined as technology that performs human-like cognitive tasks; subsequent briefings will present management advice distinct to machine learning and generative tools, respectively.

Access More Research!

Any visitor to the website can read many MIT CISR Research Briefings in the webpage. But site users who have signed up on the site and are logged in can download all available briefings, plus get access to additional content. Even more content is available to members of MIT CISR member organizations .

Author Barb Wixom reads this research briefing as part of our audio edition of the series. Follow the series on SoundCloud.

DOWNLOAD THE TRANSCRIPT

Today, everybody across the organization is hungry to know more about AI. What is it good for? Should I trust it? Will it take my job? Business leaders are investing in massive training programs, partnering with promising vendors and consultants, and collaborating with peers to identify ways to benefit from AI and avoid the risk of AI missteps. They are trying to understand how to manage AI responsibly and at scale.

Our book Data Is Everybody’s Business: The Fundamentals of Data Monetization describes how organizations make money using their data.[foot]Barbara H. Wixom, Cynthia M. Beath, and Leslie Owens, Data Is Everybody's Business: The Fundamentals of Data Monetization , (Cambridge: The MIT Press, 2023), https://mitpress.mit.edu/9780262048217/data-is-everybodys-business/ .[/foot] We wrote the book to clarify what data monetization is (the conversion of data into financial returns) and how to do it (by using data to improve work, wrap products and experiences, and sell informational solutions). AI technology’s role in this is to help data monetization project teams use data in ways that humans cannot, usually because of big complexity or scope or required speed. In our data monetization research, we have regularly seen leaders use AI effectively to realize extraordinary business goals. In this briefing, we explain how such leaders achieve big AI wins and maximize financial returns.

Using AI in Data Monetization

AI refers to the ability of machines to perform human-like cognitive tasks.[foot]See Hind Benbya, Thomas H. Davenport, and Stella Pachidi, “Special Issue Editorial: Artificial Intelligence in Organizations: Current State and Future Opportunities , ” MIS Quarterly Executive 19, no. 4 (December 2020), https://aisel.aisnet.org/misqe/vol19/iss4/4 .[/foot] Since 2019, MIT CISR researchers have been studying deployed data monetization initiatives that rely on machine learning and predictive algorithms, commonly referred to as predictive AI.[foot]This research draws on a Q1 to Q2 2019 asynchronous discussion about AI-related challenges with fifty-three data executives from the MIT CISR Data Research Advisory Board; more than one hundred structured interviews with AI professionals regarding fifty-two AI projects from Q3 2019 to Q2 2020; and ten AI project narratives published by MIT CISR between 2020 and 2023.[/foot] Such initiatives use large data repositories to recognize patterns across time, draw inferences, and predict outcomes and future trends. For example, the Australian Taxation Office (ATO) used machine learning, neural nets, and decision trees to understand citizen tax-filing behaviors and produce respectful nudges that helped citizens abide by Australia’s work-related expense policies. In 2018, the nudging resulted in AUD$113 million in changed claim amounts.[foot]I. A. Someh, B. H. Wixom, and R. W. Gregory, “The Australian Taxation Office: Creating Value with Advanced Analytics,” MIT CISR Working Paper No. 447, November 2020, https://cisr.mit.edu/publication/MIT_CISRwp447_ATOAdvancedAnalytics_SomehWixomGregory .[/foot]

In 2023, we began exploring data monetization initiatives that rely on generative AI.[foot]This research draws on two asynchronous generative AI discussions (Q3 2023, N=35; Q1 2024, N=34) regarding investments and capabilities and roles and skills, respectively, with data executives from the MIT CISR Data Research Advisory Board. It also draws on in-progress case studies with large organizations in the publishing, building materials, and equipment manufacturing industries.[/foot] This type of AI analyzes vast amounts of text or image data to discern patterns in them. Using these patterns, generative AI can create new text, software code, images, or videos, usually in response to user prompts. Organizations are now beginning to openly discuss data monetization initiative deployments that include generative AI technologies. For example, used vehicle retailer CarMax reported using OpenAI’s ChatGPT chatbot to help aggregate customer reviews and other car information from multiple data sets to create helpful, easy-to-read summaries about individual used cars for its online shoppers. At any point in time, CarMax has on average 50,000 cars on its website, so to produce such content without AI the company would require hundreds of content writers and years of time; using ChatGPT, the company’s content team can generate summaries in hours.[foot]Paula Rooney, “CarMax drives business value with GPT-3.5,” CIO , May 5, 2023, https://www.cio.com/article/475487/carmax-drives-business-value-with-gpt-3-5.html ; Hayete Gallot and Shamim Mohammad, “Taking the car-buying experience to the max with AI,” January 2, 2024, in Pivotal with Hayete Gallot, produced by Larj Media, podcast, MP3 audio, https://podcasts.apple.com/us/podcast/taking-the-car-buying-experience-to-the-max-with-ai/id1667013760?i=1000640365455 .[/foot]

Big advancements in machine learning, generative tools, and other AI technologies inspire big investments when leaders believe the technologies can help satisfy pent-up demand for solutions that previously seemed out of reach. However, there is a lot to learn about novel technologies before we can properly manage them. In this year’s MIT CISR research, we are studying predictive and generative AI from several angles. This briefing is the first in a series; in future briefings we will present management advice specific to machine learning and generative tools. For now, we present three principles supported by our data monetization research to guide business leaders when making AI investments of any kind: invest in practices that build capabilities required for AI, involve all your people in your AI journey, and focus on realizing value from your AI projects.

Principle 1: Invest in Practices That Build Capabilities Required for AI

Succeeding with AI depends on having deep data science skills that help teams successfully build and validate effective models. In fact, organizations need deep data science skills even when the models they are using are embedded in tools and partner solutions, including to evaluate their risks; only then can their teams make informed decisions about how to incorporate AI effectively into work practices. We worry that some leaders view buying AI products from providers as an opportunity to use AI without deep data science skills; we do not advise this.

But deep data science skills are not enough. Leaders often hire new talent and offer AI literacy training without making adequate investments in building complementary skills that are just as important. Our research shows that an organization’s progress in AI is dependent on having not only an advanced data science capability, but on having equally advanced capabilities in data management, data platform, acceptable data use, and customer understanding.[foot]In the June 2022 MIT CISR research briefing, we described why and how organizations build the five advanced data monetization capabilities for AI. See B. H. Wixom, I. A. Someh, and C. M. Beath, “Building Advanced Data Monetization Capabilities for the AI-Powered Organization,” MIT CISR Research Briefing, Vol. XXII, No. 6, June 2022, https://cisr.mit.edu/publication/2022_0601_AdvancedAICapabilities_WixomSomehBeath .[/foot] Think about it. Without the ability to curate data (an advanced data management capability), teams cannot effectively incorporate a diverse set of features into their models. Without the ability to oversee the legality and ethics of partners’ data use (an advanced acceptable data use capability), teams cannot responsibly deploy AI solutions into production.

It’s no surprise that ATO’s AI journey evolved in conjunction with the organization’s Smarter Data Program, which ATO established to build world-class data analytics capabilities, and that CarMax emphasizes that its governance, talent, and other data investments have been core to its generative AI progress.

Capabilities come mainly from learning by doing, so they are shaped by new practices in the form of training programs, policies, processes, or tools. As organizations undertake more and more sophisticated practices, their capabilities get more robust. Do invest in AI training—but also invest in practices that will boost the organization’s ability to manage data (such as adopting a data cataloging tool), make data accessible cost effectively (such as adopting cloud policies), improve data governance (such as establishing an ethical oversight committee), and solidify your customer understanding (such as mapping customer journeys). In particular, adopt policies and processes that will improve your data governance, so that data is only used in AI initiatives in ways that are consonant with your organization's values and its regulatory environment.

Principle 2: Involve All Your People in Your AI Journey

Data monetization initiatives require a variety of stakeholders—people doing the work, developing products, and offering solutions—to inform project requirements and to ensure the adoption and confident use of new data tools and behaviors.[foot]Ida Someh, Barbara Wixom, Michael Davern, and Graeme Shanks, “Configuring Relationships between Analytics and Business Domain Groups for Knowledge Integration, ” Journal of the Association for Information Systems 24, no. 2 (2023): 592-618, https://cisr.mit.edu/publication/configuring-relationships-between-analytics-and-business-domain-groups-knowledge .[/foot] With AI, involving a variety of stakeholders in initiatives helps non-data scientists become knowledgeable about what AI can and cannot do, how long it takes to deliver certain kinds of functionality, and what AI solutions cost. This, in turn, helps organizations in building trustworthy models, an important AI capability we call AI explanation (AIX).[foot]Ida Someh, Barbara H. Wixom, Cynthia M. Beath, and Angela Zutavern, “Building an Artificial Intelligence Explanation Capability,” MIS Quarterly Executive 21, no. 2 (2022), https://cisr.mit.edu/publication/building-artificial-intelligence-explanation-capability .[/foot]

For example, at ATO, data scientists educated business colleagues on the mechanics and results of models they created. Business colleagues provided feedback on the logic used in the models and helped to fine-tune them, and this interaction helped everyone understand how the AI made decisions. The data scientists provided their model results to ATO auditors, who also served as a feedback loop to the data scientists for improving the model. The data scientists regularly reported on initiative progress to senior management, regulators, and other stakeholders, which ensured that the AI team was proactively creating positive benefits without neglecting negative external factors that might surface.

Given the consumerization of generative AI tools, we believe that pervasive worker involvement in ideating, building, refining, using, and testing AI models and tools will become even more crucial to deploying fruitful AI projects—and building trust that AI will do the right thing in the right way at the right time.

Principle 3: Focus on Realizing Value From Your AI Projects

AI is costly—just add up your organization’s expenses in tools, talent, and training. AI needs to pay off, yet some organizations become distracted with endless experimentation. Others get caught up in finding the sweet spot of the technology, ignoring the sweet spot of their business model. For example, it is easy to become enamored of using generative AI to improve worker productivity, rolling out tools for employees to write better emails and capture what happened in meetings. But unless those activities materially impact how your organization makes money, there likely are better ways to spend your time and money.

Leaders with data monetization experience will make sure their AI projects realize value in the form of increased revenues or reduced expenses by backing initiatives that are clearly aligned with real challenges and opportunities. That is step one. In our research, the leaders that realize value from their data monetization initiatives measure and track their outcomes, especially their financial outcomes, and they hold someone accountable for achieving the desired financial returns. At CarMax, a cross-functional team owned the mission to provide better website information for used car shoppers, a mission important to the company’s sales goals. Starting with sales goals in mind, the team experimented with and then chose a generative AI solution that would enhance the shopper experience and increase sales.

Figure 1: Three Principles for Getting Value from AI Investments

The three principles are based on the following concepts from MIT CISR data research: 1. Data liquidity: the ease of data asset recombination and reuse 2. Data democracy: an organization that empowers employees in the access and use of data 3. Data monetization: the generation of financial returns from data assets

Managing AI Using a Data Monetization Mindset

AI has and always will play a big role in data monetization. It’s not a matter of whether to incorporate AI, but a matter of how to best use it. To figure this out, quantify the outcomes of some of your organization’s recent AI projects. How much money has the organization realized from them? If the answer disappoints, then make sure the AI technology value proposition is a fit for your organization’s most important goals. Then assign accountability for ensuring that AI technology is applied in use cases that impact your income statements. If the AI technology is not a fit for your organization, then don’t be distracted by media reports of the AI du jour.

Understanding your AI technology investments can be hard if your organization is using AI tools that are bundled in software you purchase or are built for you by a consultant. To set yourself up for success, ask your partners to be transparent with you about the quality of data they used to train their AI models and the data practices they relied on. Do their answers persuade you that their tools are trustworthy? Is it obvious that your partner is using data compliantly and is safeguarding the model from producing bad or undesired outcomes? If so, make sure this good news is shared with the people in your organization and those your organization serves. If not, rethink whether to break with your partner and find another way to incorporate the AI technology into your organization, such as by hiring people to build it in-house.

To paraphrase our book’s conclusion: When people actively engage in data monetization initiatives using AI , they learn, and they help their organization learn. Their engagement creates momentum that initiates a virtuous cycle in which people’s engagement leads to better data and more bottom-line value, which in turn leads to new ideas and more engagement, which further improves data and delivers more value, and so on. Imagine this happening across your organization as all people everywhere make it their business to find ways to use AI to monetize data.

This is why AI, like data, is everybody’s business.

© 2024 MIT Center for Information Systems Research, Wixom and Beath. MIT CISR Research Briefings are published monthly to update the center’s member organizations on current research projects.

Related Publications

Talking Points

Ai, like data, is everybody's business.

Working Paper: Vignette

The australian taxation office: creating value with advanced analytics.

Research Briefing

Building advanced data monetization capabilities for the ai-powered organization.

Building AI Explanation Capability for the AI-Powered Organization

What is Data Monetization?

About the researchers.

Barbara H. Wixom, Principal Research Scientist, MIT Center for Information Systems Research (CISR)

Cynthia M. Beath, Professor Emerita, University of Texas and Academic Research Fellow, MIT CISR

Mit center for information systems research (cisr).

Founded in 1974 and grounded in MIT's tradition of combining academic knowledge and practical purpose, MIT CISR helps executives meet the challenge of leading increasingly digital and data-driven organizations. We work directly with digital leaders, executives, and boards to develop our insights. Our consortium forms a global community that comprises more than seventy-five organizations.

MIT CISR Associate Members

MIT CISR wishes to thank all of our associate members for their support and contributions.

MIT CISR's Mission Expand

MIT CISR helps executives meet the challenge of leading increasingly digital and data-driven organizations. We provide insights on how organizations effectively realize value from approaches such as digital business transformation, data monetization, business ecosystems, and the digital workplace. Founded in 1974 and grounded in MIT’s tradition of combining academic knowledge and practical purpose, we work directly with digital leaders, executives, and boards to develop our insights. Our consortium forms a global community that comprises more than seventy-five organizations.