research paper about water resources

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
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 03 August 2021

Future global urban water scarcity and potential solutions

• Chunyang He   ORCID: orcid.org/0000-0002-8440-5536 1 , 2 ,
• Zhifeng Liu   ORCID: orcid.org/0000-0002-4087-0743 1 , 2 ,
• Jianguo Wu   ORCID: orcid.org/0000-0002-1182-3024 1 , 2 , 3 ,
• Xinhao Pan 1 , 2 ,
• Zihang Fang 1 , 2 ,
• Jingwei Li 4 &
• Brett A. Bryan   ORCID: orcid.org/0000-0003-4834-5641 5  

Nature Communications volume  12 , Article number:  4667 ( 2021 ) Cite this article

89k Accesses

481 Citations

163 Altmetric

Metrics details

• Environmental sciences
• Water resources

Urbanization and climate change are together exacerbating water scarcity—where water demand exceeds availability—for the world’s cities. We quantify global urban water scarcity in 2016 and 2050 under four socioeconomic and climate change scenarios, and explored potential solutions. Here we show the global urban population facing water scarcity is projected to increase from 933 million (one third of global urban population) in 2016 to 1.693–2.373 billion people (one third to nearly half of global urban population) in 2050, with India projected to be most severely affected in terms of growth in water-scarce urban population (increase of 153–422 million people). The number of large cities exposed to water scarcity is projected to increase from 193 to 193–284, including 10–20 megacities. More than two thirds of water-scarce cities can relieve water scarcity by infrastructure investment, but the potentially significant environmental trade-offs associated with large-scale water scarcity solutions must be guarded against.

Similar content being viewed by others

Guiding urban water management towards 1.5 °C

Reassessing the projections of the World Water Development Report

Urban water and electricity demand data for understanding climate change impacts on the water-energy nexus

Introduction.

The world is rapidly urbanizing. From 1950 to 2020, the global population living in cities increased from 0.8 billion (29.6%) to 4.4 billion (56.2%) and is projected to reach 6.7 billion (68.4%) by 2050 1 . Water scarcity—where demand exceeds availability—is a key determinant of water security and directly affects the health and wellbeing of urban residents, urban environmental quality, and socioeconomic development 2 , 3 , 4 , 5 , 6 . At present, many of the world’s urban populations face water scarcity 3 . Population growth, urbanization, and socioeconomic development are expected to increase urban industrial and domestic water demand by 50–80% over the next three decades 4 , 7 . In parallel, climate change will affect the spatial distribution and timing of water availability 8 , 9 . As a result, urban water scarcity is likely to become much more serious in the future 10 , 11 , 12 , potentially compromising the achievement of the United Nations Sustainable Development Goals (SDGs) especially SDG11 Sustainable Cities and Communities and SDG6 Clean Water and Sanitation 13 , 14 .

Urban water scarcity has typically been addressed via engineering and infrastructure. Reservoirs are commonly used to store water during periods of excess availability and continuously supply water to cities to avoid water shortages during dry periods 15 . Desalination plants are increasingly used to solve water deficit problems for coastal cities 16 . For cities where local water resources cannot meet demand, inter-basin water transfer can also be an effective solution 17 (Supplementary Table  8 ). However, investment in water infrastructure is costly; requires substantial human, energy, and material resources; is limited by natural conditions such as geographic location and topography; and may have very significant environmental impacts 2 , 3 , 18 . Hence, a comprehensive understanding of water scarcity and the potential solutions for the world’s cities is urgently required to promote more sustainable and livable urban futures 7 , 18 , 19 .

Previous studies have evaluated urban water scarcity 2 , 3 , 7 , 19 (Supplementary Table  3 ). However, these studies have been limited in a number of ways including: assessing only a subset of the urban population (e.g., large cities only or regional in focus); considering only part of the water scarcity problem (i.e., availability but not withdrawal); or lacking a future perspective. For example, in assessing global urban water scarcity, Flörke et al. 7 considered 482 cities (accounting for just 26% of the global urban population) under a business-as-usual scenario, and while McDonald et al. 2 assessed a larger range of cities and scenarios, they considered water availability only, not withdrawals. As a result, significant uncertainty in estimates of current and future extent of urban water-scarcity remain, varying from 0.2 to 1 billion people affected in 2000 and from 0.5 to 4 billion in 2050 (Supplementary Table  4 ). A comprehensive assessment of global urban water scarcity is needed to identify cities at risk and provide better estimates of the number of people affected.

In addition, although many studies have discussed potential solutions to urban water scarcity, few have investigated the feasibility of these solutions for water-scarce cities at the global scale. Proposed solutions include groundwater exploitation, seawater desalination, increased water storage in reservoirs, inter-basin water transfer, improved water-use efficiency, and urban landscape management 2 , 3 , 14 , 19 . However, the potential effectiveness of these solutions for the world’s water-scarce cities depends on many factors including the severity of water scarcity, urban and regional geography and hydrogeology, socio-economic characteristics, and environmental carrying capacity 7 , 20 . Pairing the identification of water scarce cities with an evaluation of potential solutions is essential for guiding investment in future urban water security.

In this study, we comprehensively assessed global urban water scarcity in 2016 and 2050 and the feasibility of potential solutions for water-scarce cities. We first quantified the spatial patterns of the global urban population for 2016 at a grid-cell resolution of 1 km 2 by integrating spatial urban land-use and population data. We then identified water-scarce areas at the catchment scale by combining global water resource availability and demand data, and calculated the global urban population in water-scarce areas in 2016. We also quantified the global urban population in water-scarce areas for 2050 under four socioeconomic and climate change scenarios by combining modeled projections of global urban area, population, and water availability and demand. Finally, we evaluated the feasibility of seven major solutions for easing water scarcity for each affected city. We discuss the implications of the results for mitigating global urban water scarcity and improving the sustainability and livability of the world’s cities.

Current urban water scarcity

Globally, 933 million (32.5%) urban residents lived in water-scarce regions in 2016 (Table  1 , Fig.  1b ) with 359 million (12.5%) and 573 million (20.0%) experiencing perennial and seasonal water scarcity, respectively. India (222 million) and China (159 million) had the highest urban populations facing water scarcity (Table  1 , Fig.  1c ).

a spatial patterns of large cities in water-scarce areas (cities with population above 10 million in 2016 were labeled). b Water-scarce urban population at the global scale. c Water-scarce urban population at the national scale (10 countries with the largest values were listed). Please refer to Supplementary Data for urban water scarcity in each catchment.

Of the world’s 526 large cities (i.e., population >1 million), 193 (36.7%) were located in water-scarce regions (96 perennial, 97 seasonal) (Fig.  1a ). Of the 30 megacities (i.e., population >10 million), 9 (30.0%) were located in water-scarce regions (Table  2 ). Six of these, including Los Angeles, Moscow, Lahore, Delhi, Bangalore, and Beijing, were located in regions with perennial water scarcity and three (Mexico City, Istanbul, and Karachi) were seasonally water-scarce (Fig.  1a ).

Urban water scarcity in 2050

At the global scale, the urban population facing water scarcity was projected to increase rapidly, reaching 2.065 (1.693–2.373) billion people by 2050, a 121.3% (81.5–154.4%) increase from 2016 (Table  1 , Fig.  2a ). 840 (476–905) million people were projected to face perennial water scarcity and 1.225 (0.902–1.647) billion were projected to face seasonal water scarcity (Table  1 ). India’s urban population growth in water-scarce regions was projected to be much higher than other countries (Fig.  2b ), increasing from 222 million people to 550 (376–644) million people in 2050 and accounting for 26.7% (19.2%–31.2%) of the world’s urban population facing water scarcity (Table  1 ).

a Changes in water-scarce urban population at the global scale. Bars present the simulated results using the ensemble mean of runoff from GCMs, the total values (i.e., perennial and seasonal), and percentages are labeled. Crosses (gray/black) present the simulated results (total/perennial) using runoff from each GCM. b Changes in water-scarce urban population at the national scale (10 countries with the largest values were listed). Bars present the total values simulated using the ensemble mean of runoff from GCMs. Crosses present the total values simulated using runoff from each GCM. Please refer to Supplementary Data for urban water scarcity in each catchment.

Nearly half of the world’s large cities were projected to be located in water-scarce regions by 2050 (Fig.  3 , Supplementary Fig.  3 ). The number of large cities facing water scarcity under at least one scenario was projected to increase to 292 (55.5%) by 2050. The number of megacities facing water scarcity under at least one scenario was projected to increase to 19 (63.3%) including 10 new megacities (i.e., Cairo, Dhaka, Jakarta, Lima, Manila, Mumbai, New York, Sao Paulo, Shanghai, and Tianjin) (Table  2 ).

Only the water-scarce cities are listed. Cities with a population >10 million in 2016 are labeled.

Factors influencing urban water scarcity

Growth in urban population and water demand will be the main factor contributing to the increase in urban water scarcity (Fig.  4 ). From 2016 to 2050, population growth, urbanization, and socioeconomic development were projected to increase water demand and contribute to an additional 0.990 (0.829–1.135) billion people facing urban water scarcity, accounting for 87.5% (80.4–91.4%) of the total increase. Climate change was projected to alter water availability and increase the urban population subject to water scarcity by 52 (−72–229) million, accounting for 4.6% (−9.0–18.4%) of the total increase.

Bars present the simulated results using the ensemble mean of runoff from GCMs, crosses present the simulated results using runoff from each GCM.

Potential solutions to urban water scarcity

Water scarcity could be relieved for 276 (94.5%) large cities, including 17 (89.5%) megacities, via the measures assessed (Table  3 , Supplementary Table  5 ). Among these, 260 (89.0%) cities have the option of implementing two or more measures. For example, Los Angeles can adopt desalination, groundwater exploitation, inter-basin water transfer, and/or virtual water trade (Table  3 ). However, 16 large cities, including two megacities (i.e., Delhi and Lahore) in India and Pakistan, are restricted by geography and economic development levels, making it difficult to adopt any of the potential water scarcity solutions (Table  3 ).

Domestic virtual water trade was the most effective solution, which could alleviate water scarcity for 208 (71.2%) large cities (including 14 (73.7%) megacities). Inter-basin water transfer could be effective for 200 (68.5%) large cities (including 14 (73.7%) megacities). Groundwater exploitation could be effective for 192 (65.8%) large cities (including 11 (57.9%) megacities). International water transfer and virtual water trade showed potential for 190 (65.1%) large cities (including 10 (52.6%) megacities). Reservoir construction could relieve water scarcity for 151 (51.7%) large cities (including 10 (52.6%) megacities). Seawater desalination has the potential to relieve water scarcity for 146 (50.0%) large cities (including 12 (63.2%) megacities). In addition, water scarcity for 68 (23.3%) large cities, including five megacities (i.e., New York, Sao Paulo, Mumbai, Dhaka, and Jakarta), could be solved via the water-use efficiency improvements, slowed population growth rate, and climate change mitigation measures considered under SSP1&RCP2.6.

We have provided a comprehensive evaluation of current and future global urban water scarcity and the feasibility of potential solutions for water-scarce cities. We found that the global urban population facing water scarcity was projected to double from 933 million (33%) in 2016 to 1.693–2.373 billion (35–51%) in 2050, and the number of large cities facing water scarcity under at least one scenario was projected to increase from 193 (37%) to 292 (56%). Among these cities, 276 large cities (95%) can address water scarcity through improving water-use efficiency, limiting population growth, and mitigating climate change under SSP1&RCP2.6; or via seawater desalination, groundwater exploitation, reservoir construction, interbasin water transfer, or virtual water trade. However, no solutions were available to relieve water scarcity for 16 large cities (5%), including two megacities (i.e., Delhi and Lahore) in India and Pakistan.

Previous studies have estimated the global urban population facing water scarcity to be between 150 and 810 million people in 2000, between 320 and 650 million people in 2010, and increasing to 0.479–1.445 billion people by 2050 (Supplementary Table  4 ). Our estimates of 933 million people in 2016 facing urban water scarcity, increasing to 1.693–2.373 billion people by 2050, are substantially higher than previously reported (Supplementary Fig.  5a ). This difference is attributed to the fact that we evaluated the exposure of all urban dwellers rather than just those living in large cities (Supplementary Table  3 ). According to United Nations census data, 42% of the world’s urban population lives in small cities with a total population of <300,000 (Supplementary Fig.  4 ). Therefore, it is difficult to fully understand the global urban water scarcity only by evaluating the exposure of large cities. This study makes up for this deficiency and provides a comprehensive assessment of global urban water scarcity.

In addition, we used spatially corrected urban population data, newly released water demand/availability data, simulated runoff from GCMs in the most recent CMIP6 database, catchment-based estimation approach covering the upstream impacts on downstream water availability, and the new scenario framework combining socioeconomic development and climate change. Such data and methods can reduce the uncertainty in the spatial distribution of urban population and water demand/availability in the future, providing a more reliable assessment of global urban water scarcity.

Our projections suggest that global urban water scarcity will continue to intensify from 2016 to 2050 under all scenarios. By 2050, near half of the global urban population was projected to live in water-scarce regions (Figs.  2 ,  3 ). This will directly threaten the realization of SDG11 Sustainable Cities and Communities and SDG6 Clean Water and Sanitation . Although 95% of water-scarce cities can address the water crisis via improvement of water-use efficiency, seawater desalination, groundwater exploitation, reservoir construction, interbasin water transfer, or virtual water trade (Supplementary Table  5 ), these measures will not only have transformative impacts on society and the economy, but will also profoundly affect the natural environment. For example, the construction of reservoirs and inter-basin water transfer may cause irreversible damage to river ecosystems and hydrogeology and change the regional climate 4 , 15 , 17 , 21 , 22 . Desalination can have serious impacts on coastal zones and marine ecosystems 16 , 23 . Virtual water trade will affect regional economies, increase transport sector greenhouse gas emissions, and may exacerbate social inequality and affect the local environments where goods are produced 19 , 24 .

Water scarcity solutions may not be available to all cities. The improvement of water-use efficiency as well as other measures require the large-scale construction of water infrastructure, rapid development of new technologies, and large economic investment, which are difficult to achieve in low- and middle-income countries by 2050 14 . In addition, there will be 16 large cities, such as Delhi and Lahore, that cannot effectively solve the water scarcity problem via these measures (Supplementary Table  5 ). These cities also face several socioeconomic and environmental issues such as poverty, rapid population growth, and overextraction and pollution of groundwater 25 , 26 , which will further affect the achievement of SDG1 No Poverty , SDG3 Good Health and Well-being , SDG10 Reduced Inequalities , SDG14 Life below Water and SDG15 Life on Land .

To address global urban water scarcity and realize the SDGs, four directions are suggested. We need to:

Promote water conservation and reduce water demand. Our assessment provides evidence that the proposed water conservation efforts under SSP1&RCP2.6 are effective, which results in the least water-scarce urban population (34–241 million fewer compared to other SSPs&RCPs) at the global scale and can mitigate water scarcity for 68 (23.3%) large cities. The application of emerging water-saving technologies and the construction of sponge cities, smart cities, low-carbon cities, and resilient cities as well as the development of new theories and methods such as landscape sustainability science, watershed science, and geodesign will also play an important role for the further water demand reduction 5 , 6 , 27 , 28 , 29 . To implement these measures, the cooperation and efforts of scientists, policy makers and the public, as well as sufficient financial and material support are required. In addition, international cooperation must be strengthened in order to promote the development and dissemination of new technologies, assist in the construction of water infrastructure, and raise public awareness of water-savings, particularly in the Global South 30 .

Control population growth and urbanization in water-scarce regions by implementing relevant policies and regional planning. Urban population growth increases both water stress and the exposure of people, making it a key driver exacerbating global urban water scarcity 2 . Hence, the limitation of urban population growth in water-scarce areas can help to address this issue. According to our estimation, the control of urbanization under SSP3&RCP7.0, which has the lowest urbanization rate among four scenarios, can reduce the urban population subject to water scarcity by 93–207 million people compared with the business-as-usual scenario (SSP2&RCP4.5) and the rapid urbanization scenario (SSP5&RCP8.5), including 80–178 million people in India alone by 2050 (Fig.  2 ). To realize this pathway, policies that encourage family planning as well as tax incentives and regional planning for promoting population migration from water-scarce areas to other areas are needed 18 . In particular, for cities such as Delhi and Lahore that are both restricted by geography and socioeconomic disadvantage and have few options for dealing with water scarcity, there is an urgent need to control urban population growth and urbanization rates.

Mitigate climate change through energy efficiency and emissions abatement measures to avoid water resource impacts caused by the change in precipitation and the increase in evapotranspiration due to increased temperature. Our contribution analysis shows that the impacts of climate change on urban water scarcity is quite uncertain (ranging from a reduction of 72 million water-scarce urban people to an increase of 229 million) under different scenarios and GCMs (Fig.  4 ). On average, climate change under the business-as-usual scenario (SSP2&RCP4.5) will increase the global water-scarce urban population by 31 million in 2050. If the emissions reduction measures under SSP1&RCP2.6 are adopted, the increase in global water-scarce urban population due to climate change will be cut by half (16 million) in 2050. Thus, mitigating climate change is also important to reducing urban water scarcity. Considering that climate change in water-scarce areas would be affected by both internal and external impacts, mitigating climate change requires a global effort 31 .

Undertake integrated local sustainability assessment of water scarcity solutions. Our assessment reveals that 208 (71.2%) large cities may address water scarcity through seawater desalination, groundwater exploitation, reservoir construction, interbasin water transfer, and/or virtual water trade (Supplementary Table  5 ). While our results provide a guide at the global scale, city-level decisions about which measures to adopt to alleviate water scarcity involve very significant investments and should be supported by detailed local assessments of their relative effectiveness weighed against the potentially significant financial, environmental, and socio-economic costs. Integrated analyses are needed to quantify the effects of potential solutions on reducing water scarcity, their financial and resource requirements, and their potential impacts on socio-economic development for water-scarce cities and the sustainability of regional environments. To guard against the potential negative impacts of these measures, comprehensive impact assessments are required before implementing them, stringent regulatory oversight and continuous environmental monitoring are needed during and after their implementation, and policies and regulations should be established to achieve the sustainable supply and equitable distribution of water resources 24 , 32 .

Uncertainty is prevalent in our results due to limitations in the methodology and data used. First, constrained by data availability, in the evaluation of urban water scarcity in 2016 we used water demand/availability data for 2014 derived from the simulation results of the PCRGLOBWB 2 model, and only considered the inter-basin water transfers listed in City Water Map and the renewable groundwater simulated from the PCRGLOBWB 2 model instead of all available groundwater 3 , 33 . In the assessment of urban water scarcity and feasibility of potential solutions in 2050, we used water demand data derived from Hanasaki et al. 34 , in which irrigated area expansion, crop intensity change, and improvement in irrigation water efficiency were considered, but the change in irrigation to adapt to climate change as well as the impacts of energy systems (e.g., bio-energy production, mining, and fossil fuel extraction) on water demand were not fully considered 35 . Second, in order to maintain consistency and comparability of the water stress index (WSI) with the PCRGLOBWB 2 outputs 33 , environmental flow requirements were not considered. Following Mekonnen and Hoekstra 36 and Veldkamp et al. 37 (2017), we used an extreme threshold for WSI of 1.0 (where the entire water available is withdrawn for human use). If a more conservative threshold (e.g., WSI = 0.4 which is the threshold defining high water stress) was used, estimated global water scarcity and the urban population exposed to water stress would be much higher 7 .

In summary, global urban water scarcity is projected to intensify greatly from 2016 to 2050. By 2050, nearly half of the global urban population (1.693–2.373 billion) were projected to live in water-scarce regions, with about one quarter concentrated in India, and 19 (63%) global megacities are expected to face water scarcity. Increases in urban population and water demand drove this increase, while changes in water availability due to climate change compounded the problem. About 95% of all water-scarce cities could find at least one potential solution, but substantial investment is needed and solutions may have significant environmental and socioeconomic consequences. The aggravation of global urban water scarcity and the consequences of potential solutions will challenge the achievement of several SDGs. Therefore, there is an urgent need to further improve water-use efficiency, control urbanization in water-scarce areas, mitigate water availability decline due to climate change, and undertake integrated sustainability analyses of potential solutions to address urban water scarcity and promote sustainable development.

Description of scenarios used in this study

To assess future urban water scarcity, we used the scenario framework from the Scenario Model Intercomparison Project (ScenarioMIP), part of the International Coupled Model Intercomparison Project Phase 6 (CMIP6) 38 . The scenarios have been developed to better link the Shared Socioeconomic Pathways (SSPs) and Representative Concentration Pathways (RCPs) to support comprehensive research in different fields to better understand global climatic and socioeconomic interactions 38 , 39 . We selected the four ScenarioMIP Tier 1 scenarios (i.e., SSP1&RCP2.6, SSP2&RCP4.5, SSP3&RCP7.0, and SSP5&RCP8.5) to evaluate future urban water scarcity. SSP1&RCP2.6 represents the sustainable development pathway of low radiative forcing level, low climate change mitigation challenges, and low social vulnerability. SSP2&RCP4.5 represents the business-as-usual pathway of moderate radiative forcing and social vulnerability. SSP3&RCP7.0 represents a higher level of radiative forcing and high social vulnerability. SSP5&RCP8.5 represents a rapid development pathway and very high radiative forcing 38 .

Estimation of urban water scarcity

To estimate urban water scarcity, we quantified the total urban population living in water-scarce areas 2 , 3 , 7 , 19 . Specifically, we first corrected the spatial distribution of the global urban population, then identified water-scarce areas around the world, and finally quantified the urban population in water-scarce areas at different scales (Supplementary Fig.  1 ).

Correcting the spatial distribution of global urban population

The existing global urban population data from the History Database of the Global Environment (HYDE) provided consistent information on historical and future population, but it has a coarse spatial resolution of 10 km (Supplementary Table  1 ) 40 , 41 . In addition, it was estimated using total population, urbanization levels, and urban population density, and does not align well with the actual distribution of urban land 42 . Hence, we allocated the HYDE global urban population data to high-resolution urban land data. We first obtained global urban land in 2016 from He et al. 42 . Since the scenarios used in existing urban land forecasts are now dated 43 , 44 , we simulated the spatial distribution of global urban land in 2050 under each SSP at a grid-cell resolution of 1km 2 using the zoned Land Use Scenario Dynamics-urban (LUSD-urban) model 45 , 46 , 47 (Supplementary Methods 1). The simulated urban expansion area in this study was significantly correlated with that in existing datasets (Supplementary Table  6 ). We then converted the global urban land raster layers for 2016 and 2050 into vector format to characterize the spatial extent of each city. The total population within each city was then summed and the remaining HYDE urban population cells located outside urban areas were allocated to the nearest city. Assuming that the population density within an urban area was homogeneous, we calculated the total population per square kilometer for all urban areas and converted this back to raster format at a spatial resolution of 1 km 2 . The new urban population data had much lower error than the original HYDE data (Supplementary Table  7 ).

Identification of global water-scarce areas

Annual and monthly WSI values were calculated at the catchment level in 2014 and 2050 as the ratio of water withdrawals (TWW) to availability (AWR) 33 . Due to limited data availability, we combined water-scarce areas in 2014 and the urban population in 2016 to estimate current urban water scarcity. WSI for catchment i for time t as:

For each catchment defined by Masutomi et al. 48 , the total water withdrawal (TWW t,i ) equalled the sum of water withdrawals (WW t , n , i ) for each sector n (irrigation, livestock, industrial, or domestic), while the water availability equalled the sum of available water resources for catchment i ( R t , i ), inflows/outflows of water resources due to interbasin water transfer ( \(\varDelta {{{{\mathrm{W{R}}}}}}_{t,i}\) ), and water resources from each upstream catchment j (WR t , i , j ):

The changes of water resources due to interbasin water transfer were calculated based on City Water Map produced by McDonald et al. 3 . The number of water resources from upstream catchment j was calculated based on its water availability (AWR t , i , j ) and water consumption for each sector n (WC t , n , i,j ) 49 :

For areas without upstream catchments, the number of available water resources was equal to the runoff. Following Mekonnen and Hoekstra 36 , and Hofste et al. 33 , we did not consider environmental flow requirements in calculating water availability.

Annual and monthly WSI for 2014 were calculated directly based on water withdrawal, water consumption, and runoff data from AQUEDUCT3.0 (Supplementary Table  1 ). The data from AQUEDUCT3.0 were selected because they are publicly available and the PCRaster Global Water Balance (PCRGLOBWB 2) model used in the AQUADUCT 3.0 can better represent groundwater flow and available water resources in comparison with other global hydrologic models (e.g., the Water Global Assessment and Prognosis (WaterGAP) model) 33 . The annual and monthly WSI for 2050 were calculated by combining the global water withdrawal data from 2000 to 2050 provided by the National Institute of Environmental Research of Japan (NIER) 34 and global runoff data from 2005 to 2050 from CMIP6 (Supplementary Table  1 ). Water withdrawal \({{{{{\mathrm{W{W}}}}}}}_{s,m,n,i}^{2050}\) in 2050 for each sector n (irrigation, industrial, or domestic), catchment i , and month m under scenario s was calculated based on water withdrawal in 2014 ( \({{{{{\mathrm{W{W}}}}}}}_{m,n,i}^{2014}\) ):

adjusted by the mean annual change in water withdrawal from 2000 to 2050 (WWR s , m , n , i ), calculated using the global water withdrawal for 2000 ( \({{{{{\mathrm{W{W}}}}}}}_{{{{{\mathrm{NIER}}}}},m,n,i}^{2000}\) ) and 2050 ( \({{{{{\mathrm{W{W}}}}}}}_{{{{{\mathrm{NIER}}}}},s,m,n,i}^{2050}\) ) provided by the NIER 34 :

Based on the assumption of a constant ratio of water consumption to water withdrawal in each catchment, water consumption in 2050 ( \({{{{{\mathrm{W{C}}}}}}}_{s,m,n,i}^{2050}\) ) was calculated as:

where \({{{{{\mathrm{W{C}}}}}}}_{m,n,i}^{2014}\) denotes water consumption in 2014. Due to a lack of data, we specified that water withdrawal for livestock remained constant between 2014 and 2050, and used water withdrawal simulation under SSP3&RCP6.0 provided by the National Institute of Environmental Research in Japan to approximate SSP3&RCP7.0.

To estimate water availability, we calculated available water resources ( \({R}_{s,m,i}^{2041-2050}\) ) for each catchment i and month m under scenario s for the period of 2041–2050 as:

based on the amount of available water resources with 10-year ordinary least square regression from 2005 to 2014 ( \({R}_{m,i}^{{{{{\mathrm{ols}}}}},\,2005-2014}\) ) from AQUEDUCT3.0 (Supplementary Table  1 ). \({\overline{R}}_{m,i}^{2005-2014}\) and \({\overline{R}}_{s,m,i}^{2041-2050}\) denote the multi-year average of runoff (i.e., surface and subsurface) from 2005 to 2014, and from 2041 to 2050, respectively, calculated using the average values of simulation results from 10 global climate models (GCMs) (Supplementary Table  2 ).

We then identified water-scarce catchments based on the WSI. Two thresholds of 0.4 and 1.0 have been used to identify water-scarce areas from WSI (Supplementary Table  4 ). While the 0.4 threshold indicates high water stress 49 , the threshold of 1.0 has a clearer physical meaning, i.e., that water demand is equal to the available water supply and environmental flow requirements are not met 36 , 37 . We adopted the value of 1.0 as a threshold representing extreme water stress to identify water-scarce areas. The catchments with annual WSI >1.0 were identified as perennial water-scarce catchments; the catchments with annual WSI equal to or <1.0 and WSI for at least one month >1.0 were identified as seasonal water-scarce catchments.

Estimation of global urban water scarcity

Based on the corrected global urban population data and the identified water-scarce areas, we evaluated urban water scarcity at the global and national scales via a spatial overlay analysis. The urban population exposed to water scarcity in a region (e.g., the whole world or a single country) is equal to the sum of the urban population in perennial water-scarce areas and that in seasonal water-scarce areas. Limited by data availability, we used water-scarce areas in 2014 and the urban population in 2016 to estimate current urban water scarcity. Projected water-scarce areas and urban population in 2050 under four scenarios were then used to estimate future urban water scarcity. In addition, we obtained the location information of large cities (with population >1 million in 2016) from the United Nations’ World Urbanization Prospects 1 (Supplementary Table  1 ) and identified those in perennial and seasonal water-scarce areas.

Uncertainty analysis

To evaluate the uncertainty across the 10 GCMs used in this study (Supplementary Table  2 ), we identified water-scarce areas and estimated urban water scarcity using the simulated runoff from each GCM under four scenarios. To perform the uncertainty analysis, the runoff in 2050 for each GCM was calculated using the following equation:

where \({R}_{s,g,m,i}^{2050}\) denotes the runoff of catchment i in month m in 2050 for GCM g under scenario s . \({R}_{g,m,i}^{2005-2014}\) and \({R}_{s,g,m,i}^{2041-2050}\) denote the multi-year average runoff from 2005 to 2014, and from 2041 to 2050, respectively, calculated using the simulation results from GCM g . Using the runoff for each GCM, the WSI in 2050 for each catchment was recalculated, water-scarce areas were identified, and the urban population exposed to water scarcity was estimated.

Contribution analysis

Based on the approach used by McDonald et al. 2 and Munia et al. 50 , we quantified the contribution of socioeconomic factors (i.e., water demand and urban population) and climatic factors (i.e., water availability) to the changes in global urban water scarcity from 2016 to 2050. To assess the contribution of socioeconomic factors ( \({{{{{\mathrm{Co{n}}}}}}}_{s,{{{{\mathrm{SE}}}}}}\) ), we calculated global urban water scarcity in 2050 while varying demand and population and holding catchment runoff constant ( \({{{{{\mathrm{UW{S}}}}}}}_{s,{{{{\mathrm{SE}}}}}}^{2050}\) ). Conversely, to assess the contribution of climate change ( \(Co{n}_{s,CC}\) ), we calculated scarcity while varying runoff and holding urban population and water demand constant ( \({{{{{\mathrm{UW{S}}}}}}}_{s,{{{{\mathrm{CC}}}}}}^{2050}\) ). Socioeconomic and climatic contributions were then calculated as:

Feasibility analysis of potential solutions to urban water scarcity

Potential solutions to urban water scarcity involve two aspects: increasing water availability and reducing water demand 2 . Approaches to increasing water availability include groundwater exploitation, seawater desalination, reservoir construction, and inter-basin water transfer; while approaches to reduce water demand include water-use efficiency measures (e.g., new cultivars for improving agricultural water productivity, sprinkler or drip irrigation for improving water-use efficiency, water-recycling facilities for improving domestic and industrial water-use intensity), limiting population growth, and virtual water trade 2 , 3 , 18 , 32 . To find the best ways to address urban water scarcity, we assessed the feasibility of these potential solutions for each large city (Supplementary Fig.  2 ).

First, we divided these solutions into seven groups according to scenario settings and the scale of implementation of each solution (Supplementary Fig.  2 ). Among the solutions assessed, water-use efficiency improvement, limiting population growth, and climate change mitigation were included in the simulation of water demand and water availability under the ScenarioMIP SSPs&RCPs simulations 34 . Here, we considered the measures within SSP1&RCP2.6 which included the lowest growth in population, irrigated area, crop intensity, and greenhouse gas emissions; and the largest improvements in irrigation, industrial, and municipal water-use efficiency 34 .

We then evaluated the feasibility of the seven groups of solutions according to the characteristics of water-scarce cities (Supplementary Fig.  2 ). Of the 526 large cities (with population >1 million in 2016 according to the United Nations’ World Urbanization Prospects), we identified those facing perennial or seasonal water scarcity under at least one scenario by 2050. We then selected the cities that no longer faced water scarcity under SSP1&RCP2.6 where the internal scenario assumptions around water-use efficiency, population growth, and climate change were sufficient to mitigate water scarcity. Following McDonald et al. 2 , 3 and Wada et al. 18 , we assumed that desalination can be a potential solution for coastal cities (distance from coastline <100 km) and groundwater exploitation can be feasible for cities where the groundwater table has not significantly declined. For cities in catchments facing seasonal water scarcity and with suitable topography, reservoir construction was identified as a potential solution. Inter-basin water transfer was identified as a potential solution for a city if nearby basins (i.e., in the same country, <1000 km away [the distance of the longest water transfer project in the world]) were not subject to water scarcity and had sufficient water resources to address the water scarcity for the city. Domestic virtual water trade was identified as a potential solution for a city if it was located in a country without national scale water scarcity. International water transfer or virtual water trade was identified as a feasible solution for cities in middle and high-income countries. Based on the above assumptions, we identified potential solutions to water scarcity in each city (see Supplementary Table  1 for the data used).

Data availability

All the data created in this study are openly available and the download information of supplementary data can be found in Github repositories with the identifier https://github.com/zfliu-bnu/Urban-water-scarcity . Other data are available from the corresponding author upon reasonable request.

United Nations (UN). 2018. 2018 Revision of World Urbanization Prospects. https://population.un.org/wup/ (2018).

McDonald, R. I. et al. Urban growth, climate change, and freshwater availability. Proc. Natl Acad. Sci. USA 108 , 6312–6317 (2011a).

Article   ADS   CAS   PubMed   PubMed Central   Google Scholar  

McDonald, R. I. et al. Water on an urban planet: Urbanization and the reach of urban water infrastructure. Glob. Environ. Change 27 , 96–105 (2014).

Article   Google Scholar  

Garrick, D. et al. Rural water for thirsty cities: a systematic review of water reallocation from rural to urban regions. Environ. Res. Lett. 14 , 043003 (2019).

Article   ADS   Google Scholar  

Krueger, E., Rao, P. S. C. & Borchardt, D. Quantifying urban water supply security under global change. Glob. Environ. Change 56 , 66–74 (2019a).

Krueger, E. H. et al. Resilience dynamics of urban water supply security and potential of tipping points. Earth’s Future 7 , 1167–1191 (2019b).

Flörke, M., Schneider, C. & McDonald, R. I. Water competition between cities and agriculture driven by climate change and urban growth. Nat. Sustainability 1 , 51–58 (2018).

Revi, A. et al., eds. Climate Change 2014: Impacts, Adaptation, and Vulnerability. Part A: Global and Sectoral Aspects. Contribution of Working Group II to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change. (Cambridge, Cambridge University Press, 2014).

Greve, P. et al. Global assessment of water challenges under uncertainty in water scarcity projections. Nat. Sustainability 1 , 486–494 (2018).

Vörösmarty, C. J., Green, P., Salisbury, J. & Lammers, R. B. Global water resources: Vulnerability from climate change and population growth. Science 289 , 284–288 (2000).

Article   ADS   PubMed   Google Scholar  

Schewe, J. et al. Multimodel assessment of water scarcity under climate change. Proc. Natl Acad. Sci. USA 111 , 3245–3250 (2014).

Article   ADS   CAS   PubMed   Google Scholar  

IPCC (Intergovernmental Panel on Climate Change). Synthesis Report. Contribution of Working Groups I, II and III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change. (Cambridge University Press, Cambridge, 2014).

United Nations (UN). Transforming Our World: The 2030 Agenda for Sustainable Development. Seventieth Session of the United Nations General Assembly Resolution A/RES/70/1. (UN, New York, 2015).

Larsen, T. A., Hoffmann, S., Luthi, C., Truffer, B. & Maurer, M. Emerging solutions to the water challenges of an urbanizing world. Science 352 , 928–933 (2016).

Di Baldassarre, G. et al. Water shortages worsened by reservoir effects. Nat. Sustainability 1 , 617–622 (2018).

Lattemann, S. & Hopner, T. Environmental impact and impact assessment of seawater desalination. Desalination 220 , 1–15 (2008).

Article   CAS   Google Scholar  

WWF. (2009). Interbasin water transfers and water scarcity in a changing world - a solution or a pipedream? WWF, Germany.

Wada, Y., Gleeson, T. & Esnault, L. Wedge approach to water stress. Nat. Geosci. 7 , 615–617 (2014).

Article   ADS   CAS   Google Scholar  

McDonald, R. I. et al. Global urban growth and the geography of water availability, quality, and delivery. Ambio 40 , 437–446 (2011b).

Article   PubMed   PubMed Central   Google Scholar  

Padowski, J. C. & Gorelick, S. M. Global analysis of urban surface water supply vulnerability. Environ. Res. Lett. 9 , 104004 (2014).

Vörösmarty, C. J. et al. Global threats to human water security and river biodiversity. Nature 467 , 555–561 (2010).

Article   ADS   PubMed   CAS   Google Scholar  

Grill, G. et al. Mapping the world’s free-flowing rivers. Nature 569 , 215–221 (2019).

Roberts, D. A., Johnston, E. L. & Knott, N. A. Impacts of desalination plant discharges on the marine environment: a critical review of published studies. Water Res. 44 , 5117–5128 (2010).

Article   CAS   PubMed   Google Scholar  

Dalin, C., Konar, M., Hanasaki, N., Rinaldo, A. & Rodriguez-Iturbe, I. Evolution of the global virtual water trade network. Proc. Natl Acad. Sci. USA 109 , 5989–5994 (2012).

Rodell, M., Velicogna, I. & Famiglietti, J. S. Satellite-based estimates of groundwater depletion in India. Nature 460 , 999–U980 (2009).

Podgorski, J. & Berg, M. Global threat of arsenic in groundwater. Science 368 , 845–850 (2020).

Wu, J. Landscape sustainability science: ecosystem services and human well-being in changing landscapes. Landsc. Ecol. 28 , 999–1023 (2013).

Cheng, G. & Li, X. Integrated research methods in watershed science. Sci. China-Earth Sci. 58 , 1159–1168 (2015).

Lin, J. et al. Reframing water-related ecosystem services flows. Ecosyst. Serv. 50 , 101306 (2021).

Fu, B., Zhang, J., Wang, S. & Zhao, W. Classification–coordination–collaboration: a systems approach for advancing Sustainable Development Goals. Natl Sci. Rev. 7 , 838–840 (2020).

Seto, K. C. et al., eds. Climate Change 2014: Mitigation of Climate Change. Contribution of Working Group III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change. (Cambridge: Cambridge University Press, 2014).

Brown, T. C., Mahat, V. & Ramirez, J. A. Adaptation to future water shortages in the United States caused by population growth and climate change. Earth’s Future 7 , 219–234 (2019).

Hofste, R. W. et al. AQUEDUCT 3.0: Updated decision-relevant global water risk indicators. In. Washington, DC: World Resources Institute. https://doi.org/10.46830/writn.18.00146 (2019).

Hanasaki, N. et al. A global water scarcity assessment under Shared Socio-economic Pathways - Part 1: Water use. Hydrol. Earth Syst. Sci. 17 , 2375–2391 (2013).

Rosa, L. et al. Potential for sustainable irrigation expansion in a 3 °C warmer climate. Proc. Natl Acad. Sci. USA 117 , 29526–29534 (2020).

Mekonnen, M. M. & Hoekstra, A. Y. Four billion people facing severe water scarcity. Sci. Adv. 2 , e1500323 (2016).

Article   ADS   PubMed   PubMed Central   Google Scholar  

Veldkamp, T. I. E. et al. Water scarcity hotspots travel downstream due to human interventions in the 20th and 21st century. Nat. Commun. 8 , 12 (2017).

O’Neill, B. C. et al. The Scenario Model Intercomparison Project (ScenarioMIP) for CMIP6. Geoscientific Model Dev. 9 , 3461–3482 (2016).

Stouffer, R. J. et al. CMIP5 scientific gaps and recommendations for CMIP6. Bull. Am. Meteorological Soc. 98 , 95–105 (2017).

Klein Goldewijk, K., Beusen, A. & Janssen, P. Long-term dynamic modeling of global population and built-up area in a spatially explicit way-HYDE 3.1. Holocene 20 , 565–573 (2010).

Klein Goldewijk, K., Beusen, A., Doelman, J. & Stehfest, E. New anthropogenic land use estimates for the Holocene-HYDE 3.2. Earth Syst. Sci. Data 9 , 927–953 (2017).

He, C. et al. Detecting global urban expansion over the last three decades using a fully convolutional network. Environ. Res. Lett. 14 , 034008 (2019).

Seto, K. C., Güneralp, B. & Hutyra, L. R. Global forecasts of urban expansion to 2030 and direct impacts on biodiversity and carbon pools. Proc. Natl Acad. Sci. USA 109 , 16083–16088 (2012).

Güneralp, B. & Seto, K. C. Futures of global urban expansion: uncertainties and implications for biodiversity conservation. Environ. Res. Lett. 8 , 14025 (2013).

He, C., Okada, N., Zhang, Q., Shi, P. & Li, J. Modelling dynamic urban expansion processes incorporating a potential model with cellular automata. Landsc. Urban Plan. 86 , 79–91 (2008).

He, C., Zhao, Y., Huang, Q., Zhang, Q. & Zhang, D. Alternative future analysis for assessing the potential impact of climate change on urban landscape dynamics. Sci. Total Environ. 532 , 48–60 (2015).

Liu, Z., Yang, Y., He, C. & Tu, M. Climate change will constrain the rapid urban expansion in drylands: a scenario analysis with the zoned Land Use Scenario Dynamics-urban model. Sci. Total Environ. 651 , 2772–2786 (2019).

Masutomi, Y., Inui, Y., Takahashi, K. & Matsuoka, Y. Development of Highly Accurate Global Polygonal Drainage Basin Data. Hydrological Process. 23 , 572–584 (2009).

Gassert, F., Luck, M., Landis, M., Reig, P. & Shiao, T. Aqueduct Global Maps 2.1: Constructing Decision-Relevant Global Water Risk Indicators. In. Washington, DC: World Resources Institute. https://www.wri.org/research/aqueduct-global-maps-21 (2014).

Munia, H. A. et al. Future transboundary water stress and its drivers under climate change: a global study. Earth’s Future 8 , e2019EF001321 (2020).

Download references

Acknowledgements

We thank Prof. N. Hanasaki (National Institute for Environmental Studies, Tsukuba, Japan) and Dr. Rutger W. Hofste (World Resources Institute, Washington, DC, USA) for providing global water demand/availability data. This work was supported by the Second Tibetan Plateau Scientific Expedition and Research Program (Grant No. 2019QZKK0405) and the National Natural Science Foundation of China (Grant No. 41871185 & 41971270). It was also supported by the project from the State Key Laboratory of Earth Surface Processes and Resource Ecology, China.

Author information

Authors and affiliations.

Center for Human-Environment System Sustainability (CHESS), State Key Laboratory of Earth Surface Processes and Resource Ecology (ESPRE), Beijing Normal University, Beijing, China

Chunyang He, Zhifeng Liu, Jianguo Wu, Xinhao Pan & Zihang Fang

School of Natural Resources, Faculty of Geographical Science, Beijing Normal University, Beijing, China

School of Life Sciences and School of Sustainability, Arizona State University, Tempe, AZ, USA

School of Environmental and Geographical Sciences (SEGS), Shanghai Normal University, Shanghai, China

Centre for Integrative Ecology, Deakin University, Melbourne, Australia

Brett A. Bryan

You can also search for this author in PubMed   Google Scholar

Contributions

C.H., Z.L., J.W., and B.B. designed the study and planned the analysis. Z.L., X.P., Z.F., and J.L. did the data analysis. C.H., Z.L., and B.B. drafted the manuscript. All authors contributed to the interpretation of findings, provided revisions to the manuscript, and approved the final manuscript.

Corresponding author

Correspondence to Zhifeng Liu .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Peer review information Nature Communications thanks Helen Baron, Robert McDonald and Lorenzo Rosa for their contribution to the peer review of this work.

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

Supplementary information

Supplementary information, rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

He, C., Liu, Z., Wu, J. et al. Future global urban water scarcity and potential solutions. Nat Commun 12 , 4667 (2021). https://doi.org/10.1038/s41467-021-25026-3

Download citation

Received : 30 October 2020

Accepted : 15 July 2021

Published : 03 August 2021

DOI : https://doi.org/10.1038/s41467-021-25026-3

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

Visual analysis method for unmanned pumping stations on dynamic platforms based on data fusion technology.

EURASIP Journal on Advances in Signal Processing (2024)

Global river economic belts can become more sustainable by considering economic and ecological processes

• Alistair George Liam Borthwick

Communications Earth & Environment (2024)

Ultra-fast green hydrogen production from municipal wastewater by an integrated forward osmosis-alkaline water electrolysis system

• Gabriela Scheibel Cassol

Nature Communications (2024)

Electronic structure modulation of iron sites with fluorine coordination enables ultra-effective H2O2 activation

• Jinming Luo

Structure integration and architecture of solar-driven interfacial desalination from miniaturization designs to industrial applications

• Chenyang Dang
• Yunteng Cao
• Meifang Zhu

Nature Water (2024)

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

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

Sign up for the Nature Briefing: Anthropocene newsletter — what matters in anthropocene research, free to your inbox weekly.

Artificial Intelligence for Water Consumption Assessment: State of the Art Review

• Open access
• Published: 25 April 2024

Cite this article

You have full access to this open access article

• Almando Morain 1 ,
• Nivedita Ilangovan 2 ,
• Christopher Delhom 3 &
• Aavudai Anandhi   ORCID: orcid.org/0000-0002-5323-1983 4  

340 Accesses

Explore all metrics

In recent decades, demand for freshwater resources has increased the risk of severe water stress. With the growing prevalence of artificial intelligence (AI), many researchers have turned to it as an alternative to linear methods to assess water consumption (WC). Using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework, this study utilized 229 screened publications identified through database searches and snowball sampling. This study introduces novel aspects of AI's role in water consumption assessment by focusing on innovation, application sectors, sustainability, and machine learning applications. It also categorizes existing models, such as standalone and hybrid, based on input, output variables, and time horizons. Additionally, it classifies learnable parameters and performance indexes while discussing AI models' advantages, disadvantages, and challenges. The study translates this information into a guide for selecting AI models for WC assessment. As no one-size-fits-all AI model exists, this study suggests utilizing hybrid AI models as alternatives. These models offer flexibility regarding efficiency, accuracy, interpretability, adaptability, and data requirements. They can address the limitations of individual models, leverage the strengths of different approaches, and provide a better understanding of the relationships between variables. Several knowledge gaps were identified, resulting in suggestions for future research.

Similar content being viewed by others

Water treatment and artificial intelligence techniques: a systematic literature review research

Intelligent Water Resources Management

Artificial Intelligence for Water Supply Systems

Avoid common mistakes on your manuscript.

1 Introduction

Water is used for various purposes, including drinking, fire control, garden irrigation, cleaning, and industrial and agricultural processes (Morain and Anandhi 2022 ). A significant water resource management challenge is ensuring sufficient water to meet human needs (de Souza Groppo et al. 2019 ). Over the past few years, water resources have become increasingly vulnerable due to several factors, including climate change, population growth, city size, commercial and social conditions of people, supply costs, development of global industries, overexploitation of sea resources, land use/land cover change, and water distribution characteristics (Anele et al. 2017 ; Anandhi and Kannan 2018 ; Yang et al. 2023 ). Monitoring and forecasting water consumption (WC) are among the most critical aspects of making informed decisions to ensure water sustainability (Arsene et al. 2022 ). Over the last few decades, considerable research has been conducted on using AI models as alternatives to statistical models for estimating and forecasting WC (Alhendi et al. 2022 ). Several studies, such as Liu et al. ( 2022 ), Pacchin et al. ( 2019 ), and Rahmati et al. ( 2014 ), have tested and compared different AI forecasting models by consideration of their accuracy, performance, and application convenience. In their respective papers, Liu et al. ( 2019a , b ), Vijayalaksmi and Babu ( 2015 ), and Wang and Liu ( 2016 ) applied single AI models to forecast WC, while Altunkaynak and Nigussie ( 2018 ) and González Perea et al. ( 2018 ) used multiple models. Similarly, other studies have used AI models to estimate WC (Wei et al. 2022 ), monitor consumption, extract and cluster consumption events, and predict WC sources (Arsene et al. 2022 ).

Numerous review articles have addressed different aspects of AI applications in water consumption. Rahim et al. ( 2020 ) reviewed the contributions and limitations of AI models in digital water metering. Surendra and Deka ( 2022 ) and Niknam et al. ( 2022 ) discussed the use of artificial neural network (ANN), fuzzy logic (FL), adaptive neuro fuzzy inference systems (ANFIS), and wavelet transforms (WA) in residential WC. Drogkoula et al. ( 2023 ) investigated machine learning (ML) methodologies in water management. The potential of evolutionary computation as a subfield of AI has been reviewed concerning water demand management policies (Oyebode and Ighravwe 2019 ). An analysis of Strengths, Weaknesses, Opportunities, and Threats (SWOT) was conducted on AI-driven technologies as facilitators or barriers to sustainable development goals, reviewing smart water management and AI applications in agriculture and sanitation services (Palomares et al. 2021 ). Additionally, some reviews have focused on the application of ANN in the drinking water sector (O’Reilly et al. 2018 ), Internet of Things in agriculture (Madushanki et al. 2019 ), FL in hydrology and water resources (Kambalimath and Deka 2020 ) and agriculture (Jha et al. 2019 ), and Bayesian approach to water systems in buildings (Wong and Mui 2018 ).

Despite the coverage of AI applications in water consumption assessment in previous review articles, several unaddressed aspects necessitate further investigation. Therefore, the novelty of this study lies in the following:

Presenting four focus points of AI's role in water consumption assessment: innovation, application sector, sustainability, and machine learning applications.

Synthesizing and classifying existing models (e.g., standalone, combined/hybrid) along with their input and output variables and time horizons.

Classifying learnable parameters (e.g., weights and biases) and performance indexes.

Synthesizing the advantages, disadvantages, and challenges associated with AI models.

Translating synthesis to guide AI model selection based on efficiency, accuracy, interpretability, adaptability, and data requirements.

Identifying knowledge gaps and providing recommendations for future work.

The findings will benefit many stakeholders, including environmental agencies, researchers, practitioners, citizens and communities, municipal governments, utility companies and water managers, and policymakers.

2 Methodology

2.1 article selection process.

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol was used to consolidate the scientific knowledge presented in this study. Three major multidisciplinary research databases, Google Scholar ( http://scholar.google.com/ ), EBSCO ( https://www.ebsco.com/ ), and Springer ( https://link.springer.com/ ) were used to identify relevant studies related to this topic. An initial search using the keywords "artificial intelligence" and "water consumption" retrieved 363,000 documents on July 29, 2022. A more streamlined second search was conducted on August 12, 2022, using additional key terms, such as forecasting, prediction, estimation, assessment, machine learning, deep learning, and artificial neural networks. This reduced the number to 262 peer-reviewed articles and were downloaded for full-text review. A third search was conducted on January 10th, 2024, using the same terms to include a few studies (10) from 2023 to enhance the quality of the paper. Snowball sampling was conducted to gather additional studies (29) to identify methods for assigning weights and biases to AI models.

2.2 Quality Assessment and Study Selection Process

The downloaded articles were evaluated for the systematic review. After applying inclusion and exclusion criteria (assessing, judging, and identifying potential bias risks, and appraising internal or external validity; Supplementary Figure A ), 72 papers were excluded from the final analysis. Ultimately, 190 papers were selected from the two first searches (July 29 and August 12, 2024), 10 from the third search (January 10th, 2024), and 29 from the snowball sampling, resulting in 229 studies considered for this paper (Fig.  1 ).

PRISMA flowchart for article inclusion/exclusion in this systematic review

2.3 Data Extraction and Analysis Methods

General characteristics, such as year of publication, keywords, authors and co-authors, and country of origin of the authors and co-authors of the study were extracted from 190 studies. AI model characteristics such as inputs and outputs, learnable parameter determination methods, performance indices, challenges, and advantages and disadvantages of some AI models were also collected. The information generated in this systematic review was analyzed and presented using multiple visualization methods. Line graphs (yearly distribution of publications), network maps (keywords, authors, and co-author collaboration), geographical maps (country of origin of authors and co-authors), pie charts (purpose of the studies), tables (AI models, input, output, sector of application), collapsible trees (learnable parameter determination methods), tree maps (performance indexes), and other figures (AI implications and system model in WC assessment) were created. A network collaboration map was created using VOSviewer (more details in the supplementary material ). A geographical map was created using MapChart ( https://www.mapchart.net/world.html ). Tables were created using Microsoft Word, and custom figures were created using PowerPoint. Microsoft Excel was used to design the treemap, CollapsibleTree was created using R (Version 4.2.3.), and MATLAB (Version R2023b) was used to generate the line graph and pie charts. The trend in the number of publications is considered one of the prominent measures to assess the significance and emergence of certain technologies within the subject domain.

3.1 Descriptive Aspects of the Studies

Between 2016 and 2021, there was a significant increase in publications on AI-based WC research. More than half of the total studies (64%) were published in the last six years (an average of 18 publications per year), in contrast to 61 publications that were published during the first 17 years of the period (an average of 3.5/year). Interest in AI applications related to WC has increased over the past decade, as indicated below (dotted line in Fig.  2 a).

a Spatial distribution according to the country affiliation of authors and co-authors; b Annual distribution of the studies; c Purpose of the studies

A total of 720 authors produced the articles used in this study . The authors and co-authors are geographically affiliated with 22 Asian countries, seven American countries, one country in Oceania, and six African countries. China (16.8%), Spain (8.9%), India (8.4%), Iran (7.8%), the United Kingdom, and Brazil (5.7%) were the top six countries with the highest numbers of authors (Fig.  2 b). The publication rates were highest in Asian countries. Moreover, a co-authorship analysis showed that the author Hussein Al-Bugharbe had the highest number of documents and total link strength (documents:4; total link strength:17), followed by Manuel Herrera (Number of documents:4; total link strength:12). These two authors were productive researchers who actively collaborated on research publications.

Furthermore, a cluster analysis revealed four significant collaborations between the authors. Hussein Al-Bugharbee's cluster researched AI applications for predicting urban WC, while Manuel Herrera's cluster focused on using hybrid AI models to forecast short-term urban water demand. Other clusters, such as Plinio Centoamore's, aimed to explore the benefits of implementing AI in industrial WC, while Michael Blumenstein's cluster examined residential WC (Supplementary Figure B ). These findings suggest that only a few scholars have established a pattern of close collaboration and contact with AI applications in WC assessment studies. Therefore, AI experts should cooperate more effectively in studies related to WC assessment. Additionally, most studies on AI applications have focused on evaluating urban WC. Thus, more studies are needed to use AI techniques to assess agricultural and industrial WC in addition to urban WC.

The selected studies for this paper have compared different AI models, predicted WC, reviewed the literature, estimated current WC, and managed and monitored water supply systems (Fig.  2 c). Review papers constituted 9% of the 190 publications included in this study. The reviews were on industries, agriculture, water planning, and governance. They highlight various aspects of AI Model applications for predictive analytics, smart metering, leak detection, and AI-driven decision support systems. This paper also conducted a keyword analysis to highlight the core concepts emerging from this study. The analysis has underscored the prevalence of keywords like "water demand," "water consumption," "forecasting," and "prediction," thereby highlighting the significance of distinguishing between the concepts of "water demand" and "water consumption," as well as "forecasting" and "prediction." This distinction is crucial, as these terms are frequently used interchangeably by different authors. The analysis also revealed the use of various AI models, with ANNs emerging as the prevalent model for estimating water consumption. More details are provided in the supplementary material .

3.2 Water Consumption: Artificial Intelligence Implications

Figure  3 illustrates the relevance of AI in WC assessment from four perspectives: innovation, application, sustainability, and machine learning.

Implications of AI in water consumption assessment

3.2.1 Innovation

The recent rise in AI has led to numerous innovations in science and society. Notable examples include implementing smart cities, where technologically modern urban areas use electronic methods and sensors to collect, analyze, and integrate critical information related to water systems (Preciado et al. 2019 ; Kamyab et al. 2023 ). Smart water networks, incorporating smart water meters (Candelieri et al. 2015 ) and sensors, are developed to continuously monitor and diagnose problems, prioritize and manage maintenance issues, and optimize water distribution networks using real-time data (Barroso et al. 2022 ; Stańczyk et al. 2023 ). Additionally, AI-driven innovations have extended to smart irrigation systems in agriculture and urban landscape management (Bhoi et al. 2021 ). This utilizes self-adaptive systems that optimize control decisions by considering natural terrain characteristics (Borodychev and Lytov 2021 ) and crop water requirements to tailor automatic watering schedules (González Perea et al. 2019 ). Furthermore, AI has also catalyzed advancements in computer software (e.g., MATLAB, R, and Python) by creating a need for proper programming tools to train, validate, and test AI models (Awad and Zaid-Alkelani 2019 ; Antzoulatos et al. 2020 ). These software tools have strong visualization and plotting capabilities and provide access to numerous libraries and packages for classical and modern AI models (Trajer et al. 2021 ).

3.2.2 Applications

AI applications were used for a variety of functions. (1) Monitoring household real-time WC through smart meters, detecting plumbing system anomalies, increasing water accessibility, and identifying consumer needs (Alcocer-Yamanaka et al. 2012 ). Forecasting urban residential WC, determining key water end-use categories, and monitoring drinking water distribution systems with greater efficiency and accuracy (Bennett et al. 2013 ; Al-Zahrani and Abo-Monasar 2015 ). (2) For improving agricultural WC forecasts and irrigation scheduling (Ehret et al. 2011 ; Borodychev and Lytov 2021 ). Smart irrigation systems are equipped with wireless monitoring sensors for automated crop irrigation, which can lead to improved water efficiency and increased crop yield (Bhoi et al. 2021 ). (3) For detecting waste and overuse in industrial water monitoring systems, reducing water costs and improving operational decisions (Murali et al. 2021 ). AI has also facilitated data collection in wastewater management, improved dam operation safety, and flood risk mitigation in cities (Gomes et al. 2020 ). Additionally, AI can assist construction cost management by accurately forecasting WC (Peng et al. 2020 ; Murali et al. 2021 ). (4) for assessing ecological WC (Guo and Yu 2021 ). Implementing AI in dam management has offered significant environmental benefits by augmenting water availability and ensuring efficient water distribution to populations (Gomes et al. 2020 ).

3.2.3 Sustainability

Increased WC can lead to the depletion and scarcity of water resources. Introducing AI into water management systems in areas with limited water resources and regions affected by climate change is a promising approach to ensure the sustainability of water resources (Bülbül and Öztürk 2022 ). Smart technologies such as smart meters, automatic sprinklers, and rain sensors can support water conservation. AI can detect dam leaks, improve water distribution efficiency, and prevent water wastage (Gomes et al. 2020 ; Glynis et al. 2023 ). Developing successful water management plans and policies requires effective water governance through cross-scale and cross-level interactions (Palomares et al. 2021 ). AI can provide accurate data, solve complex problems, and manage large amounts of data (Uhlenbrook et al. 2022 ). These accurate estimates and predictions are crucial for sustainable water governance.

3.2.4 Machine Learning

The use of ML has increased in various fields in the era of big data technology (Sun et al. 2021 ). In addition to enhancing the estimation techniques, it provides insights into how multiple models work together by understanding their functionalities and the impact of modifying their parameters (Ambrosio et al. 2019 ). ML models can be categorized into supervised learning, which utilizes labeled data to learn the data structure, and unsupervised learning, which operates on unlabeled data to autonomously to learn the data structure (Ghalehkhondabi et al. 2017 ; González Perea et al. 2019 ). Supervised approaches are generally more accurate (Gourmelon et al. 2021 ). However, combining unsupervised ML clustering models with supervised ML forecasting models improved performance significantly (Bata et al. 2020 ), reduced training data requirements, and lowered certain model implementation barriers (Bethke et al. 2021 ). The following section discusses these models in detail.

3.3 AI Models Used for WC Forecasting

AI models can forecast WC based on past and present observations (Anele et al. 2017 ). Additionally, the AI models forecast WC based on the time horizon categorized as short- (one hour to one week), medium- (one week to one year), or long-term (one year and more) (Babel and Shinde 2011 ; Alhendi et al. 2022 ). They are classified as standalone and combined models. More details are provided in Supplementary Tables 1 and 2 regarding the models, application sectors, input and output variables, and time horizon.

3.3.1 Standalone AI Models

Artificial Neural Networks

ANNs are ML algorithms created to replicate the structure and functionality of the human brain. These models consist of interconnected artificial neurons (nodes) arranged in layers, with each layer element fully connected to the next (Niknam et al. 2022 ). Each node in the input layer receives a distinct input variable, and the nodes in the hidden layers transform these inputs using a series of nonlinear functions before producing an output in the final layer (Nunes Carvalho et al. 2021 ). A typical example of an ANN is represented by simplified Eq.  1 (Nunes Carvalho et al. 2021 ) where Y k is the output, f outer is the output layer transfer function, f inner is the input layer transfer function, and W is the weight and bias.

They can learn complex patterns and relationships in data, making them highly beneficial for tasks that may be challenging when using non-AI models (Babel and Shinde 2011 ). Various ANNs, such as GRNN (General Regression Neural Network) (Al-Zahrani and Abo-Monasar 2015 ), CCNN (Cascade Correlation Neural Network) (Firat et al. 2010 ), FFNN (Feed Forward Neural Network) (Firat et al. 2009 ), and BPNN (Back-propagation Neural Network) (Liu et al. 2019b ) have been used as standalone models to predict domestic WC. The FFCNN (Feed Forward Computational Neural Networks) provided precise irrigation predictions when input data from the preceding two days were used (Pulido-Calvo et al. 2007 ). Other ANNs, such as MLP (Multilayer Perceptron), were used to predict urban WC based on meteorological data (Babel and Shinde 2011 ; Setiyowati et al. 2019 ). Similarly, LSTM (Long Short-Term Memory) forecasted domestic WC using similar data (Gautam et al. 2020 ; Kim et al. 2022 ). The BPNN and MLP are the most commonly used neural networks (NN) (Tian and Xue 2017 ; Liu et al. 2019b ). NNs generally comprise multiple layers of interconnected nodes.

Support Vector Machines (SVM) and Relevance Vector Machines (RVM)

The SVM is based on the concept that nonlinear trends in the input space can be mapped to linear trends in a higher-dimensional feature space, and it recognizes subtle patterns in complex datasets using a learning algorithm (Ghalehkhondabi et al. 2017 ). SVM transforms the space where two classes are only separable by a nonlinear line into a new space where it is now possible to separate the classes using a linear line, also known as a hyperplane, for higher-dimensional problems (Antunes et al. 2018 ). Using meteorological data, Gautam et al. ( 2020 ) employed an SVM to forecast domestic WC. Bhoi et al. ( 2021 ) used an SVM to suggest irrigation to farmers to reduce water waste based on data such as air temperature, soil temperature, humidity, and soil moisture. Wang and Liu ( 2016 ) proposed the application of an RVM) as a sparse probability model based on an SVM. They claimed fewer relevant vectors were used for RVM training than SVM. For regression problems, support vector regression (SVR) can be used (Antunes et al. 2018 ). SVR employs the same principles as SVM for classification; instead of finding the best hyperplane to separate the data, SVR aims to determine the best data regression hyperplane (Ambrosio et al. 2019 ). Because the general equation for SVM is not explicitly provided in the selected articles in this study, a general equation for SVR (Setiyowati et al. 2019 ) is provided in Eq.  2 where Y is the output, K ( xi , xj ) is the kernel function, x is the testing input data, α* i is the Lagrange multiplier, and λ is a scalar variable.

Other AI-based models

Regression models were used to estimate the impact of the changes in a group of independent variables on the dependent variable, making them particularly useful for predicting future demand. However, limiting the timeframe for such predictions is essential in maintaining their validity (Niknam et al. 2022 ). Although regression models are typically associated with statistical models, multiple AI options are available for regression analyses. One particularly successful model is the random forest (RF) approach, which involves growing simple trees that produce numerical response values (Niknam et al. 2022 ). The predictor set was randomly selected from the same distribution for all the trees (Ambrosio et al. 2019 ). Multiple RF has been used to forecast urban WC using vegetation indices, evapotranspiration, land cover, and satellite-derived irrigation maps (Hof and Wolf 2014 ; Wei et al. 2022 ). Other models, such as regression and decision trees, are supervised algorithms that use a tree structure to build prediction models for classification or regression purposes (Villarin and Rodriguez-Galiano 2019 ; Jurišević et al. 2021 ). The general equation for RF is provided in Eq.  3 (Nunes Carvalho et al. 2021 ), where x i is the vector of the independent variables, T b (x i ) is a single regression tree grown using bootstrapped samples and a subset of variables. N is the number of regression trees Chen et al. ( 2017 ).

k-means, SOM, DWT, and CWT

In addition to the aforementioned AI models, other models for assessing WC have been identified. These models include k-means, self-organizing maps (SOM), and WA. They are valuable tools in data analysis and preprocessing for AI tasks. k-means and SOM are unsupervised learning algorithms that cluster data points based on similarities. Bethke et al. ( 2021 ) used k-means to categorize residential water events based on appliance end-use information. Similarly, Leitão et al. ( 2019 ) used the same model to detect urban WC patterns, whereas Ioannou et al. ( 2021 ) preferred using SOM based on household needs and behaviors. Another approach for analyzing WC data is to use WA, specifically continuous and discrete wavelet transforms. Zubaidi et al. ( 2020a ) used WA to forecast urban water demand. These transforms help identify patterns in time-series data, making them valuable tools for analyzing WC over time. The typical equations for discrete and continuous wavelet transforms (DWT and CWT) are provided in Eq.  4 (Zubaidi et al. 2020a ) and Eq.  5 (Altunkaynak and Nigussie 2017 ), where \(\Psi\) (n) is the mother wavelet, while m and k are the scaling and shifting indices.

3.3.2 Combined AI Models

This study also reviewed hybrid models, which can be combinations of two or more AI models or non-AI and AI models, aiming to address the limitations of individual models and improve their accuracy and efficiency (Altunkaynak and Nigussie 2018 ; González Perea et al. 2018 ). Cutore et al. ( 2008 ) developed the SCEM-UA ANN (Shuffled Complex Evolution Metropolis Algorithm), Farah et al. ( 2019 ) used the FFBP-ANN (Feed-Forward Back-Propagation), and Zubaidi et al. ( 2020a , b ) developed the SMA-ANN (Slime Mould Algorithm), BSA-ANN (Backtracking Search Algorithm), and CSA-ANN (Crow Search Algorithm) models to forecast residential and commercial WC. Altunkaynak and Nigussie ( 2017 , 2018 ) developed four hybrid models, DWT-MLP, MSA-MLP (Multiplicative Season Algorithm), FOD-MLP (First Order Differencing), and LD-MLP (Linear Detrending), to predict monthly urban WC. In addition, Said et al. ( 2021 ) found that combining deep-learning neural networks (DLNN) with MLP, CNN (Convolutional Neural Networks), or LSTM models resulted in more accurate WC predictions than using these models alone. A collaborative model combines the RCG (Residual Correction-based Gray) and LSTM models to generate accurate real-time predictions of WC (Li et al. 2021 ). Other AI models, such as clustering algorithms, decision trees, when combined with ANNs and SVM, have been shown to improve water demand forecasting accuracy (Adamowski and Karapataki 2010 ; González Perea et al. 2018 ). With AI technologies continuing to evolve, hybrid models are likely to become increasingly important in solving complex problems and making accurate predictions (Wang et al. 2023 ). These models can address the limitations of individual models, take advantage of the strengths of different approaches, and provide a better understanding of the relationships between variables. Refer to Appendix A for further details regarding the abbreviations.

Fuzzy models with AI models are also popular models to analyze WC and hydrological systems (Ghalehkhondabi et al. 2017 ). These systems deal with uncertain or imprecise data and are based on fuzzy logic principles that allow the assignment of partial truths or degrees of membership to data points rather than the binary truth values of traditional logic (Yurdusev and Firat 2009 ). Originally developed to explain human thinking and decision-making processes, fuzzy systems have been adapted to AI to model various engineering systems, including water resources (Yurdusev and Firat 2009 ). Zubaidi et al. ( 2020a ) used ANFIS to predict urban WC. ANFIS is a combination of NN and fuzzy inference systems (Vijayalaksmi and Babu 2015 ). Oliveira et al. ( 2009 ) used fuzzy logic to model the water demand in building supply systems. Fuzzy cognitive maps were used to create a concrete water usage process from a wastewater management perspective and to predict WC (Markovič 2018 ; Sánchez-Barroso et al. 2023 ). Xu and Qin ( 2015 ) proposed a novel superiority-inferiority-based sequential fuzzy programming model to support water supply–demand analysis under uncertainty. Altunkaynak et al. ( 2005 ) used the Fuzzy Takagi–Sugeno model to forecast WC based on past monthly data, whereas Surendra and Deka ( 2012 ) used daily data for the same purpose. Surendra et al. ( 2022 ) used the Mamdani fuzzy inference system (MFIS) to estimate WC using rainfall, maximum temperature, minimum temperature, and relative humidity data. The Fuzzy Takagi–Sugeno model is among the most widely used fuzzy models. Further details are provided by Altunkaynak et al. ( 2005 ) .

3.4 AI Model Performance

3.4.1 learnable parameters: weight and bias.

Weights and biases play a crucial role in the training process of AI models by governing how the model processes the input data, assigns significance to different features, and produces output predictions. The accuracy of the outputs is highly dependent on these (dos Santos and Pereira Filho 2014 ). In NNs, weights represent the strength of the connections between different nodes, which determine how much influence the output of one neuron has on the input of another (Maltais and Gosselin 2021 ). Bias allows the model to adjust the output values of the node, regardless of the input (Adamowski and Karapataki 2010 ). Various methods exist for assigning weights and biases to AI models (Supplementary Figure D a). They can be broadly classified into initialization and optimization methods. Initialization methods help set the initial values of the weights and biases within a model, whereas optimization methods are tasked with adjusting the initial weight and bias values (Balduzzi et al. 2017 ; Narkhede et al. 2022 ). Optimization methods are primarily data-driven and rely heavily on available data to update the learnable parameters during training (Maltais and Gosselin 2021 ). Initialization methods can be classified as random initialization or data-driven initialization (Narkhede et al. 2022 ). There are also other initialization methods, such as equal, inverse weighting (Abdollahi and Ebrahimi 2020 ), and zero initialization methods (Narkhede et al. 2022 ). Random initialization methods, in which numerical values are selected from random distributions, remain the most popular due to simplicity and ease of implementation (Narkhede et al. 2022 ). Although some of these methods may not be effective for complex problems or deep networks (Balduzzi et al. 2017 ). Variance-scaling-based (a type of random initialisation method) and data-driven initialization can lead to better performance and faster convergence, particularly for complex problems or deep networks, because it helps prevent vanishing or exploding gradients (Ioffe and Szegedy 2015 ; Narkhede et al. 2022 ). Data-driven methods require domain expertise to select the correct initialization and optimization method.

3.4.2 Performance Indexes

Performance indexes are statistical methods used to analyze the residual errors between measured and predicted values and point out their differences (Banihabib and Mousavi-Mirkalaei 2019 ). They provide a way to measure algorithms' accuracy, efficiency, and effectiveness (Alhendi et al. 2022 ). The most common indexes used include the root mean square error (RSME, Eq.  6 , (Huang et al. 2021 )), mean absolute percentage error (MAPE, Eq.  7 , (Zubaidi et al. 2020b ; Sardinha-Lourenço et al. 2018 )), and the coefficient of determination (R 2 , Eq.  8 , (Adamowski and Karapataki 2010 )). The RMSE is used for tasks that minimize the difference between the predicted and actual values (Altunkaynak et al. 2005 ; Al-Zahrani and Abo-Monasar 2015 ). The MAPE is also used to measure the accuracy of forecasting models by measuring the difference between the observed and predicted values and providing a percentage error between the actual and forecasted values (Adamowski 2008 ; Firat et al. 2010 ). The smaller the error value, the better the model's performance (Jain et al. 2001 ). In contrast, R 2 measures how well the model fits the data to establish a connection between the input and output variables (Adamowski 2008 ). The higher the value of R 2 , the more accurate the model (Leon et al. 2020 ). Selecting an appropriate performance index for a model relies on data characteristics and model objectives. n is the number of observations, \(\overline{{\text{Y}} }\) is the data set mean, Ŷ i is the forecasted water demand, and Y i is the actual water demand. Supplementary Figure D b and Table  4 provide more performance indexes and their equations.

3.5 Advantages, Disadvantages, and Challenges Associated with AI Models

AI models have demonstrated effectiveness in estimating and forecasting WC (Jurišević et al. 2021 ; Kim et al. 2022 ). They can analyze large datasets to make accurate and reliable predictions. They identify hidden patterns and trends in WC data. AI models can be continuously updated with new data, allowing them to adapt and improve over time. They work with complex systems and incomplete data sets and offer high flexibility and convenience (Vozhehova et al. 2019 ; Peng et al. 2020 ). Hybrid models (SCEM-UA and ANN) can help determine model prediction uncertainties (Cutore et al. 2008 ) and can perform (BSA-ANN) even when missing factors exist (Zubaidi et al. 2020c ). A combination of CSA and ANN can accurately forecast WC based on several statistical and graphical tests (Zubaidi et al. 2020a ). Fuzzy models require minimal processing time and produce consistent predictions even with slight input-value changes (Altunkaynak et al. 2005 ). Some models (ANNs, DLNN, UWM-Id) require large amounts of data for training and validation and have a risk of not being able to generalize findings beyond the observed data (Gao et al. 2020 ; Said et al. 2021 ). While hybrid models improve predictions, some (BSA-ANN, FFBP-ANN) have relatively slow overall running times (Farah et al. 2019 ; Zubaidi et al. 2020c ). BPNN can accurately predict WC but with poor generalization (Liu et al. 2019a , b ). Due to slow convergence, MFIS has a limited performance with many inputs and outputs (Surendra et al. 2022 ). RF can become slow and ineffective with too many trees (Hof and Wolf 2014 ) and determining input weights for SOMs is challenging (Ioannou et al. 2021 ).

Several challenges exist in applying AI for WC assessment. One major challenge is finding a high-performing AI model that is easy to interpret and requires minimal data (Adamowski 2008 ). Reproducibility is another challenge due to insufficient details researchers provide regarding the variables and model training (Cutore et al. 2008 ). The type of input variables and poor-quality data can adversely affect AI model performance. These challenges further exacerbate the issue of standardization because of the lack of a normalized performance evaluation and variable selection method (Nunes Carvalho et al. 2021 ). Data may not be readily available even when the correct input variables are identified. In addition, data uncertainty can be a real challenge, and its unaccountability can sometimes lead to inaccurate estimates and forecasts (Adamowski et al. 2012 ). Data privacy is also a significant concern, as high-resolution WC data from smart meters may reveal personal information about consumers (Fu et al. 2022 ; Richards et al. 2023 ).

3.6 Knowledge Gaps

A detailed analysis of the articles resulted in the identification of the following knowledge gaps.

Most AI application studies have focused on assessing urban WC. More focus is needed on agricultural and industrial WC and water use to support the environment.

AI models used to assess WC are typically evaluated using scattered or discontinuous data due to limitations in data availability. Complete and continuous datasets should be used to assess AI models for more accurate performance evaluation (Gourmelon et al. 2021 ).

Water leaks significantly affect WC estimates and predictions. A rapid and reliable AI model for detecting water leaks can help develop effective mitigation strategies and adaptation plans (Benítez et al. 2019 ).

k-means clustering is the most commonly used clustering method associated with AI-based analysis. However, k-means is more efficient with smaller datasets and requires more time to classify large datasets. Therefore, other clustering models, such as Clustering Large Applications based on RANdom Search (CLARANS), Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH), and Clustering Using Representatives (CURE), should be investigated (Rahim et al. 2020 ).

Reproducing AI model applications can often be challenging due to the lack of reported details regarding their testing, training, and variables. Standards must be established to select the appropriate data types, variables, and performance evaluation methods to enhance the reproducibility and transparency of the process (Casali et al. 2022 ).

4 Discussions

4.1 ai for wc assessment: panoramic view and model selection.

Over the past decade, growing interest in AI has revolutionized WC prediction, modeling, and decision-making methodologies. Numerous studies have been conducted on the application of AI to WC assessments. However, most of these studies have focused on evaluating urban WC, neglecting agricultural and industrial WC, even though agriculture accounts for a significant portion of the total WC (Wei et al. 2022 ). The lack of collaboration among researchers may limit the potential of experts from diverse backgrounds to collaborate more effectively on various aspects of WC. Improved collaboration could also enhance public understanding of the importance of AI and its role in daily life and the environment, particularly concerning the four perspectives of innovation (smart cities, irrigation, meters, and software), application (agriculture, domestic, industry, and environment), sustainability (water conservation and policy/governance), and ML approaches and models, as illustrated in Fig.  3 .

AI can simulate current and future WC through standalone and combined (hybrid) AI models. Ensuring the use of high-performance models is of utmost importance, for accurate and reliable estimates and predictions. The interpretation of reasonable accuracy in the AI models depends on the performance index utilized. For instance, a higher R 2 value indicates superior model performance (Banihabib and Mousavi-Mirkalaei 2019 ), whereas a lower error (e.g., MAPE, MSE) is preferred for an ideal model (Farah et al. 2019 ; Gao et al. 2020 ). It is essential to compare the results of studies using different performance indexes, and other considerations might be necessary. For instance, MSA efficiently forecasts WC for specific urban areas (Altunkaynak and Nigussie 2017 ). To generalize the results, further studies should be conducted to determine model performance across different geographical and climatic regions, as local factors may affect predictions (Tang et al. 2012 ). AI models can also forecast WC considering climate change (Ehteram et al. 2021 ). Other considerations include studying the relationship between WC and the season (Gelažanskas and Gamage 2015 ; Gautam et al. 2020 ). The following question remains: What are the critical aspects to be considered when selecting an AI model?

Choosing the appropriate model is critical for effectively accomplishing a task. No one-size-fits-all AI model exists for WC assessment. It is crucial to establish the context of this work, whether it involves estimating or forecasting WC. In addition, defining the scope can help identify the most suitable AI model for each scenario while considering the available technologies to support AI applications. The reliability of any study depends significantly on the data used. Certain AI models may require specific technical input data, such as historical WC (Wu et al. 2020 ), meteorological (e.g., precipitation, temperature) (Tao et al. 2023 ), demographic (e.g., population, household size) (Roushangar and Alizadeh 2018 ), socio-economic (e.g., education, water price) (Azadeh et al. 2012 ; Bashar et al. 2023 ), remote sensing (e.g., dam reservoir images, spatial data) (Gonzalez Perea et al. 2021 ; Sorkhabi et al. 2022 ), and agricultural (e.g., crop fraction, irrigated area) (Ehret et al. 2011 ). Therefore, the proper variables must be selected based on the scenario and the scope of the research.

Selecting an appropriate AI model depends not only on the chosen variables and data availability but also on the model type and performance level. Figure  4 summarizes the main groups of AI models used for this purpose regarding their efficiency, accuracy, interpretability, adaptability, and data requirements (Niknam et al. 2022 ). Each of these factors can affect the performance of an AI model and should be carefully evaluated to select the most suitable model for a particular task. Efficiency is crucial for real-time applications because it relates to the model's ability to process data quickly. Accuracy determines how closely the model's predictions match the actual data. Interpretability is important because it enables users to understand how a model makes predictions. Adaptability refers to the ability of the model to adjust to new data and changing circumstances. Data requirements are related to the amount and type of data required to train the model. Models that require large amounts of data may be challenging to train and not suited for all applications. Similarly, models that require highly specialized data may not be practical in all cases.

AI system model in water management

Because the models are presented in broad categories, some may not be adequately represented. For instance, RF, classified as a regression model, often provides "high" accurate predictions, while regression, in general, provides "medium" accurate predictions (Niknam et al. 2022 ). An ideal model is efficient, accurate, interpretable, adaptable, and requires minimal data. Unfortunately, no such model has been developed yet. Therefore, the best approach is to select a model that closely fits the specific situation. Based on the current literature, the authors suggest hybrid models could be a relatively good alternative for estimating and forecasting WC because they exhibit moderate efficiency, high accuracy, medium interpretability, high adaptability, and high data requirements.

4.2 Assumptions, Limitations, and the Next Step

This study was conducted using the PRISMA framework, which was chosen due to its transparent procedures. Peer-reviewed papers were searched on July 29, 2022, August 12, 2022, and January 10th, 2024, using specific search words presented in Section  2.1 . Some studies may have been missed, as the search terms were not explicitly mentioned in their titles and abstracts. Different search timelines may have yielded different sets of studies. Therefore, the results do not reflect all available information about AI applications in WC assessments. However, the selected documents contain the information necessary to draw valid and reliable conclusions. Other considerations must be considered in the co-authorship and keyword analyses. For this study, authors who collaborated on two or more documents and keywords with a frequency of five or more in the titles and abstracts of the articles were included. The results would have differed if different selection conditions had been used. Nonetheless, these findings are highly relevant for future scientific research on estimating and forecasting WC. The next step in this research involves assessing the WC in Florida under scenarios of land-use/land cover change using hybrid AI models. The results will be informative for water governance, policy, and decision-making perspectives.

5 Conclusion

This review highlights the valuable role of AI in assessing WC, specifically its involvement from the perspectives of innovation, application, sustainability, and ML applications. Despite the growing interest in AI over the past decade, the findings of this study suggest that only a few authors have established a pattern of close collaboration and contact regarding AI applications in WC assessment studies. It was also found that nonlinear models applied to assess WC, optimization of water resource allocation, and management of water shortages have provided numerous advantages over linear models. Advantages include time-saving, accurate estimates and forecasts, convenience and flexibility, and handling complex systems and vast amounts of data. Despite numerous advantages of AI applications in WC assessments, challenges associated with reproducibility, method standardization, data availability, data uncertainty, and data privacy were highlighted. A significant challenge is selecting the appropriate model with high performance for estimating and forecasting WC. Although various models have been used in the literature, it remains unclear which model performs better, and the selection process must consider several criteria related to performance, data availability, and problem complexity. No one-size-fits-all AI model exists; this study suggests applying hybrid AI models, as they offer flexibility regarding efficiency, accuracy, interpretability, adaptability, and data requirements. Hybrid models can address the limitations of individual models, take advantage of the strengths of different approaches, and provide a better understanding of the relationships between variables. This synthesis has resulted in innovative resources to support the estimation and forecasting of WC and future studies to address challenges, respond to needs, and fill the gaps highlighted in this study.

Data Availability

The data supporting this study’s findings are available on request from the corresponding author, A.A.

Abdollahi H, Ebrahimi SB (2020) A new hybrid model for forecasting Brent crude oil price. Energy 200:117520. https://doi.org/10.1016/j.energy.2020.117520

Article   Google Scholar  

Adamowski JF (2008) Peak daily water demand forecast modeling using artificial neural networks. J Water Resour Plann Manage 134:119–128. https://doi.org/10.1061/(ASCE)0733-9496(2008)134:2(119)

Adamowski J, Karapataki C (2010) Comparison of multivariate regression and artificial neural networks for peak urban water-demand forecasting: evaluation of different ANN learning algorithms. J Hydrol Eng 15:729–743. https://doi.org/10.1061/(ASCE)HE.1943-5584.0000245

Adamowski J, Fung Chan H, Prasher SO et al (2012) Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada: water demand forecasting using wavelet-neural networks. Water Resour Res 48. https://doi.org/10.1029/2010WR009945

Alcocer-Yamanaka VH, Tzatchkov VG, Arreguin-Cortes FI (2012) Modeling of drinking water distribution networks using stochastic demand. Water Resour Manage 26:1779–1792. https://doi.org/10.1007/s11269-012-9979-2

Alhendi AA, Al-Sumaiti AS, Elmay FK et al (2022) Artificial intelligence for water–energy nexus demand forecasting: a review. Int J Low-Carbon Technol 17:730–744. https://doi.org/10.1093/ijlct/ctac043

Altunkaynak A, Nigussie TA (2017) Monthly water consumption prediction using season algorithm and wavelet transform-based models. J Water Resour Plann Manage 143:04017011. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000761

Altunkaynak A, Nigussie TA (2018) Monthly water demand prediction using wavelet transform, first-order differencing and linear detrending techniques based on multilayer perceptron models. Urban Water J 15:177–181. https://doi.org/10.1080/1573062X.2018.1424219

Altunkaynak A, Özger M, Çakmakci M (2005) Water consumption prediction of Istanbul city by using fuzzy logic approach. Water Resour Manage 19:641–654. https://doi.org/10.1007/s11269-005-7371-1

Al-Zahrani MA, Abo-Monasar A (2015) Urban residential water demand prediction based on artificial neural networks and time series models. Water Resour Manage 29:3651–3662. https://doi.org/10.1007/s11269-015-1021-z

Ambrosio JK, Brentan BM, Herrera M et al (2019) Committee machines for hourly water demand forecasting in water supply systems. Math Probl Eng 2019:1–11. https://doi.org/10.1155/2019/9765468

Anandhi A, Kannan N (2018) Vulnerability assessment of water resources – translating a theoretical concept to an operational framework using systems thinking approach in a changing climate: case study in Ogallala Aquifer. J Hydrol 557:460–474. https://doi.org/10.1016/j.jhydrol.2017.11.032

Anele A, Hamam Y, Abu-Mahfouz A, Todini E (2017) Overview, comparative assessment and recommendations of forecasting models for short-term water demand prediction. Water 9:887. https://doi.org/10.3390/w9110887

Antunes A, Andrade-Campos A, Sardinha-Lourenço A, Oliveira MS (2018) Short-term water demand forecasting using machine learning techniques. J Hydroinf 20:1343–1366. https://doi.org/10.2166/hydro.2018.163

Antzoulatos G, Mourtzios C, Stournara P et al (2020) Making urban water smart: the SMART-WATER solution. Water Sci Technol 82:2691–2710. https://doi.org/10.2166/wst.2020.391

Arsene D, Predescu A, Pahonțu B et al (2022) Advanced strategies for monitoring water consumption patterns in households based on IoT and machine learning. Water 14:2187. https://doi.org/10.3390/w14142187

Awad M, Zaid-Alkelani M (2019) Prediction of water demand using artificial neural networks models and statistical model. IJISA 11:40–55. https://doi.org/10.5815/ijisa.2019.09.05

Azadeh A, Neshat N, Hamidipour H (2012) Hybrid fuzzy regression-artificial neural network for improvement of short-term water consumption estimation and forecasting in uncertain and complex environments: case of a large Metropolitan city. J Water Resour Plann Manage 138:71–75. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000152

Babel MS, Shinde VR (2011) Identifying prominent explanatory variables for water demand prediction using artificial neural networks: a case study of Bangkok. Water Resour Manage 25:1653–1676. https://doi.org/10.1007/s11269-010-9766-x

Balduzzi D, Frean M, Leary L et al (2017) The shattered gradients problem: if resnets are the answer, then what is the question? In: Proceedings of the 34th international conference on machine learning. Proc Mach Learn Res 70:342–350

Banihabib ME, Mousavi-Mirkalaei P (2019) Extended linear and nonlinear auto-regressive models for forecasting the urban water consumption of a fast-growing city in an arid region. Sustain Cities Soc 48:101585. https://doi.org/10.1016/j.scs.2019.101585

Barroso S, Bustos P, Núñez P (2022) Towards a cyber-physical system for sustainable and smart building: a use case for optimising water consumption on a SmartCampus. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-021-03656-1

Bashar AM, Nozari H, Marofi S et al (2023) Investigation of factors affecting rural drinking water consumption using intelligent hybrid models. Water Sci Eng 16:175–183. https://doi.org/10.1016/j.wse.2022.12.002

Bata M, Carriveau R, Ting DS-K (2020) Short-term water demand forecasting using hybrid supervised and unsupervised machine learning model. Smart Water 5:2. https://doi.org/10.1186/s40713-020-00020-y

Benítez R, Ortiz-Caraballo C, Preciado JC et al (2019) A short-term data based water consumption prediction approach. Energies 12:2359

Bennett C, Stewart RA, Beal CD (2013) ANN-based residential water end-use demand forecasting model. Expert Syst Appl 40:1014–1023. https://doi.org/10.1016/j.eswa.2012.08.012

Bethke GM, Cohen AR, Stillwell AS (2021) Emerging investigator series: disaggregating residential sector high-resolution smart water meter data into appliance end-uses with unsupervised machine learning. Environ Sci: Water Res Technol 7:487–503. https://doi.org/10.1039/D0EW00724B

Bhoi A, Nayak RP, Bhoi SK et al (2021) IoT-IIRS: Internet of Things based intelligent-irrigation recommendation system using machine learning approach for efficient water usage. PeerJ Comput Sci 7:e578. https://doi.org/10.7717/peerj-cs.578

Borodychev VV, Lytov MN (2021) Irrigation management information system model with integrated elements of artificial intelligence. IOP Conf Ser: Earth Environ Sci 786:012019. https://doi.org/10.1088/1755-1315/786/1/012019

Bülbül MA, Öztürk C (2022) Optimization, modeling and implementation of plant water consumption control using genetic algorithm and artificial neural network in a hybrid structure. Arab J Sci Eng 47:2329–2343. https://doi.org/10.1007/s13369-021-06168-4

Candelieri A, Soldi D, Archetti F (2015) Short-term forecasting of hourly water consumption by using automatic metering readers data. Procedia Eng 119:844–853. https://doi.org/10.1016/j.proeng.2015.08.948

Casali Y, Aydin NY, Comes T (2022) Machine learning for spatial analyses in urban areas: a scoping review. Sustain Cities Soc 85:104050. https://doi.org/10.1016/j.scs.2022.104050

Chen G, Long T, Xiong J, Bai Y (2017) Multiple random forests modelling for urban water consumption forecasting. Water Resour Manage 31:4715–4729. https://doi.org/10.1007/s11269-017-1774-7

Cutore P, Campisano A, Kapelan Z et al (2008) Probabilistic prediction of urban water consumption using the SCEM-UA algorithm. Urban Water J 5:125–132. https://doi.org/10.1080/15730620701754434

de Souza GG, Costa MA, Libânio M (2019) Predicting water demand: a review of the methods employed and future possibilities. Water Supply 19:2179–2198. https://doi.org/10.2166/ws.2019.122

dos Santos CC, Pereira Filho AJ (2014) Water demand forecasting model for the metropolitan area of São Paulo, Brazil. Water Resour Manage 28:4401–4414. https://doi.org/10.1007/s11269-014-0743-7

Drogkoula M, Kokkinos K, Samaras N (2023) A comprehensive survey of machine learning methodologies with emphasis in water resources management. Appl Sci 13:12147. https://doi.org/10.3390/app132212147

Article   CAS   Google Scholar  

Ehret DL, Hill BD, Helmer T, Edwards DR (2011) Neural network modeling of greenhouse tomato yield, growth and water use from automated crop monitoring data. Comput Electron Agric 79:82–89. https://doi.org/10.1016/j.compag.2011.07.013

Ehteram M, Ferdowsi A, Faramarzpour M et al (2021) Hybridization of artificial intelligence models with nature inspired optimization algorithms for lake water level prediction and uncertainty analysis. Alex Eng J 60:2193–2208. https://doi.org/10.1016/j.aej.2020.12.034

Farah E, Abdallah A, Shahrour I (2019) Prediction of water consumption using Artificial Neural Networks modelling (ANN). MATEC Web Conf 295:01004. https://doi.org/10.1051/matecconf/201929501004

Firat M, Yurdusev MA, Turan ME (2009) Evaluation of artificial neural network techniques for municipal water consumption modeling. Water Resour Manage 23:617–632. https://doi.org/10.1007/s11269-008-9291-3

Firat M, Turan ME, Yurdusev MA (2010) Comparative analysis of neural network techniques for predicting water consumption time series. J Hydrol 384:46–51. https://doi.org/10.1016/j.jhydrol.2010.01.005

Fu G, Jin Y, Sun S et al (2022) The role of deep learning in urban water management: a critical review. Water Res 223:118973. https://doi.org/10.1016/j.watres.2022.118973

Gao X, Zeng W, Shen Y et al (2020) Integrated deep neural networks-based complex system for urban water management. Complexity 2020:1–12. https://doi.org/10.1155/2020/8848324

Gautam J, Chakrabarti A, Agarwal S et al (2020) Monitoring and forecasting water consumption and detecting leakage using an IoT system. Water Supply 20:1103–1113. https://doi.org/10.2166/ws.2020.035

Gelažanskas L, Gamage K (2015) Forecasting hot water consumption in residential houses. Energies 8:12702–12717. https://doi.org/10.3390/en81112336

Ghalehkhondabi I, Ardjmand E, Young WA, Weckman GR (2017) Water demand forecasting: review of soft computing methods. Environ Monit Assess 189:313. https://doi.org/10.1007/s10661-017-6030-3

Glynis K, Kapelan Z, Bakker M, Taormina R (2023) Leveraging transfer learning in LSTM neural networks for data-efficient burst detection in water distribution systems. Water Resour Manage 37:5953–5972. https://doi.org/10.1007/s11269-023-03637-3

Gomes MG, da Silva VHC, Pinto LFR et al (2020) Economic, environmental and social gains of the implementation of artificial intelligence at dam operations toward industry 4.0 principles. Sustainability 12:3604. https://doi.org/10.3390/su12093604

González Perea R, Camacho Poyato E, Montesinos P, Rodríguez Díaz JA (2018) Prediction of applied irrigation depths at farm level using artificial intelligence techniques. Agric Water Manag 206:229–240. https://doi.org/10.1016/j.agwat.2018.05.019

González Perea R, Camacho Poyato E, Montesinos P, Rodríguez Díaz JA (2019) Optimisation of water demand forecasting by artificial intelligence with short data sets. Biosys Eng 177:59–66. https://doi.org/10.1016/j.biosystemseng.2018.03.011

Gonzalez Perea R, Ballesteros R, Ortega JF, Moreno MÁ (2021) Water and energy demand forecasting in large-scale water distribution networks for irrigation using open data and machine learning algorithms. Comput Electron Agric 188:106327. https://doi.org/10.1016/j.compag.2021.106327

Gourmelon N, Bayer S, Mayle M et al (2021) Implications of experiment set-ups for residential water end-use classification. Water 13:236. https://doi.org/10.3390/w13020236

Guo T, Yu H (2021) Evaluation of ecological water consumption in Yanhe river basin based on big data. Comput Intell Neurosci 2021:1–12. https://doi.org/10.1155/2021/2201964

Hof A, Wolf N (2014) Estimating potential outdoor water consumption in private urban landscapes by coupling high-resolution image analysis, irrigation water needs and evaporation estimation in Spain. Landsc Urban Plan 123:61–72. https://doi.org/10.1016/j.landurbplan.2013.12.010

Huang H, Zhang Z, Song F (2021) An ensemble-learning-based method for short-term water demand forecasting. Water Resour Manage 35:1757–1773. https://doi.org/10.1007/s11269-021-02808-4

Ioannou AE, Creaco EF, Laspidou CS (2021) Exploring the effectiveness of clustering algorithms for capturing water consumption behavior at household level. Sustainability 13:2603. https://doi.org/10.3390/su13052603

Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning. Proc Mach Learn Res 37:448–456

Jain A, Kumar Varshney A, Chandra Joshi U (2001) Short-term water demand forecast modelling at IIT Kanpur using artificial neural networks. Water Resour Manage 15:299–321. https://doi.org/10.1023/A:1014415503476

Jha K, Doshi A, Patel P, Shah M (2019) A comprehensive review on automation in agriculture using artificial intelligence. Artif Intell Agric 2:1–12. https://doi.org/10.1016/j.aiia.2019.05.004

Jurišević NM, Gordić DR, University of Kragujevac, Faculty of Engineering, Sestre Janjića 6, 34000 Kragujevac, Serbia et al (2021) Assessment of predictive models for estimation of water consumption in public preschool buildings. JER. https://doi.org/10.36909/jer.10941

Kambalimath S, Deka PC (2020) A basic review of fuzzy logic applications in hydrology and water resources. Appl Water Sci 10:191. https://doi.org/10.1007/s13201-020-01276-2

Kamyab H, Khademi T, Chelliapan S et al (2023) The latest innovative avenues for the utilization of artificial Intelligence and big data analytics in water resource management. Results Eng 20:101566. https://doi.org/10.1016/j.rineng.2023.101566

Kim J, Lee H, Lee M et al (2022) Development of a deep learning-based prediction model for water consumption at the household level. Water 14:1512. https://doi.org/10.3390/w14091512

Leitão J, Simões N, Sá Marques JA et al (2019) Detecting urban water consumption patterns: a time-series clustering approach. Water Supply 19:2323–2329. https://doi.org/10.2166/ws.2019.113

Leon LP, Chaplot B, Solomon A (2020) Water consumption forecasting using soft computing – a case study Trinidad & Tobago. Water Supply 20:3576–3584

Li H, Chen X, Guo Z et al (2021) Data-driven peer-to-peer blockchain framework for water consumption management. Peer-to-Peer Netw Appl 14:2887–2900. https://doi.org/10.1007/s12083-021-01121-6

Liu J, Zhao L, Mao Y (2019a) Bayesian regularized NAR neural network based short-term prediction method of water consumption. E3S Web Conf 118:03024. https://doi.org/10.1051/e3sconf/201911803024

Liu L, Li W, Liu X (2019b) Prediction of daily water consumption of residential communities based on correlation analysis and BP neural network. IOP Conf Ser: Earth Environ Sci 371:032019. https://doi.org/10.1088/1755-1315/371/3/032019

Liu X, Zhang Y, Zhang Q (2022) Comparison of EEMD-ARIMA, EEMD-BP and EEMD-SVM algorithms for predicting the hourly urban water consumption. J Hydroinf 24:535–558. https://doi.org/10.2166/hydro.2022.146

Madushanki AR, Halgamuge MN, Wirasagoda WS, Syed A (2019) Adoption of the Internet of Things (IoT) in agriculture and smart farming towards urban greening: a review. IJACSA 10. https://doi.org/10.14569/IJACSA.2019.0100402

Maltais L-G, Gosselin L (2021) Predictability analysis of domestic hot water consumption with neural networks: from single units to large residential buildings. Energy 229:120658. https://doi.org/10.1016/j.energy.2021.120658

Markovič G (2018) Wastewater management using artificial intelligence. E3S Web Conf 45:00050. https://doi.org/10.1051/e3sconf/20184500050

Morain A, Anandhi A (2022) Fresh water use in Florida: trends and drivers. Water 14:3726

Murali S, Krishnan VS, Amulya PR et al (2021) Energy and water consumption pattern in seafood processing industries and its optimization methodologies. Clean Eng Technol 4:100242. https://doi.org/10.1016/j.clet.2021.100242

Narkhede MV, Bartakke PP, Sutaone MS (2022) A review on weight initialization strategies for neural networks. Artif Intell Rev 55:291–322. https://doi.org/10.1007/s10462-021-10033-z

Niknam A, Zare HK, Hosseininasab H et al (2022) A critical review of short-term water demand forecasting tools—what method should I use? Sustainability 14:5412. https://doi.org/10.3390/su14095412

Nunes Carvalho TM, de Souza Filho F de A, Porto VC (2021) Urban water demand modeling using machine learning techniques: case study of Fortaleza, Brazil. J Water Resour Plann Manage 147:05020026. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001310

O’Reilly G, Bezuidenhout CC, Bezuidenhout JJ (2018) Artificial neural networks: applications in the drinking water sector. Water Supply 18:1869–1887. https://doi.org/10.2166/ws.2018.016

Oliveira L, Gonçalves O, Uchida C (2009) Performance evaluation of dual-flush WC cistern in a multifamily building in Brazil. Build Serv Eng Res Technol 30:27–36. https://doi.org/10.1177/0143624408098445

Oyebode O, Ighravwe DE (2019) Urban water demand forecasting: a comparative evaluation of conventional and soft computing techniques. Resources 8:156. https://doi.org/10.3390/resources8030156

Pacchin E, Gagliardi F, Alvisi S, Franchini M (2019) A comparison of short-term water demand forecasting models. Water Resour Manage 33:1481–1497. https://doi.org/10.1007/s11269-019-02213-y

Palomares I, Martínez-Cámara E, Montes R et al (2021) A panoramic view and swot analysis of artificial intelligence for achieving the sustainable development goals by 2030: progress and prospects. Appl Intell 51:6497–6527. https://doi.org/10.1007/s10489-021-02264-y

Peng H, Wu H, Wang J, Dede T (2020) Research on the prediction of the water demand of construction engineering based on the BP neural network. Adv Civ Eng 2020:1–11. https://doi.org/10.1155/2020/8868817

Preciado JC, Prieto ÁE, Benitez R et al (2019) A high-frequency data-driven machine learning approach for demand forecasting in smart cities. Sci Program 2019:1–16. https://doi.org/10.1155/2019/8319549

Pulido-Calvo I, Montesinos P, Roldán J, Ruiz-Navarro F (2007) Linear regressions and neural approaches to water demand forecasting in irrigation districts with telemetry systems. Biosys Eng 97:283–293. https://doi.org/10.1016/j.biosystemseng.2007.03.003

Rahim MS, Nguyen KA, Stewart RA et al (2020) Machine learning and data analytic techniques in digital water metering: a review. Water 12:294. https://doi.org/10.3390/w12010294

Rahmati SH, Haddad OB, Sedghi H (2014) A comparison of anfis, ann, arma & multivariable regression methods for urban water-consumption forecasting, considering impacts of climate change: a case study on Tehran Mega City. Indian J Sci Res 7:870–880

Richards CE, Tzachor A, Avin S, Fenner R (2023) Rewards, risks and responsible deployment of artificial intelligence in water systems. Nat Water 1:422–432. https://doi.org/10.1038/s44221-023-00069-6

Roushangar K, Alizadeh F (2018) Investigating effect of socio-economic and climatic variables in urban water consumption prediction via Gaussian process regression approach. Water Supply 18:84–93. https://doi.org/10.2166/ws.2017.100

Said NM, Zin ZM, Ismail MN, Bakar TA (2021) Univariate water consumption time series prediction using deep learning in neural network (DLNN). IJATEE 8:473–483. https://doi.org/10.19101/IJATEE.2020.762165

Sánchez-Barroso G, González-Domínguez J, Almeida-Fernandes JP, García-Sanz-Calcedo J (2023) A fuzzy cognitive map-based algorithm for predicting water consumption in Spanish healthcare centres. Build Simul 16:2193–2205. https://doi.org/10.1007/s12273-023-1028-y

Sardinha-Lourenço A, Andrade-Campos A, Antunes A, Oliveira MS (2018) Increased performance in the short-term water demand forecasting through the use of a parallel adaptive weighting strategy. J Hydrol 558:392–404. https://doi.org/10.1016/j.jhydrol.2018.01.047

Setiyowati D, Alamsyah A, Muslim MA (2019) Water consumption prediction of semarang water utilities using support vector regression radial basic function kernel method. J Adv Inf Syst Technol 1:55–63. https://doi.org/10.15294/jaist.v1i1.36502

Sorkhabi OM, Shadmanfar B, Kiani E (2022) Monitoring of dam reservoir storage with multiple satellite sensors and artificial intelligence. Results Eng 100542. https://doi.org/10.1016/j.rineng.2022.100542

Stańczyk J, Pałczyński K, Dzimińska P et al (2023) The impact of the number of high temporal resolution water meters on the determinism of water consumption in a district metered area. Sci Rep 13:18921. https://doi.org/10.1038/s41598-023-46086-z

Sun L, Zhang H, Fang C (2021) Data security governance in the era of big data: status, challenges, and prospects. Data Sci Manag 2:41–44. https://doi.org/10.1016/j.dsm.2021.06.001

Surendra HJ, Deka PC (2022) Municipal residential water consumption estimation techniques using traditional and soft computing approach: a review. Water Conserv Sci Eng 7:77–85. https://doi.org/10.1007/s41101-022-00127-2

Surendra HJ, Deka PC, Rajakumara HN (2022) Application of Mamdani model-based fuzzy inference system in water consumption estimation using time series. Soft Comput. https://doi.org/10.1007/s00500-022-06966-4

Surendra HJ, Deka PC (2012) Effects of statistical properties of dataset in predicting performance of various artificial intelligence techniques for urban water consumption time series. Int J Civ Eng 3:426–436

Tang ZQ, Liu G, Xu WN et al (2012) Water demand forecasting in Hubei province with BP neural network model. AMR 599:701–704. https://doi.org/10.4028/www.scientific.net/AMR.599.701

Tao M, Zhang T, Xie X, Liang X (2023) Water footprint modeling and forecasting of cassava based on different artificial intelligence algorithms in Guangxi, China. J Clean Prod 382:135238. https://doi.org/10.1016/j.jclepro.2022.135238

Tian T, Xue H (2017) Prediction of annual water consumption in Guangdong Province based on Bayesian neural network. IOP Conf Ser: Earth Environ Sci 69:012032. https://doi.org/10.1088/1755-1315/69/1/012032

Trajer J, Winiczenko R, Dróżdż B (2021) Analysis of water consumption in fruit and vegetable processing plants with the use of artificial intelligence. Appl Sci 11:10167. https://doi.org/10.3390/app112110167

Uhlenbrook S, Yu W, Schmitter P, Smith DM (2022) Optimising the water we eat—rethinking policy to enhance productive and sustainable use of water in agri-food systems across scales. Lancet Planetary Health 6:e59–e65. https://doi.org/10.1016/S2542-5196(21)00264-3

Vijayalaksmi DP, Babu KSJ (2015) Water supply system demand forecasting using adaptive neuro-fuzzy inference system. Aquat Procedia 4:950–956. https://doi.org/10.1016/j.aqpro.2015.02.119

Villarin MC, Rodriguez-Galiano VF (2019) Machine learning for modeling water demand. J Water Resour Plann Manage 145:04019017. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001067

Vozhehova RA, Lykhovyd PV, Lavrenko SO et al (2019) Artificial neural network use for sweet corn water consumption prediction depending on cultivation technology peculiarities. Res J Pharm Biol Chem Sci 10:354–358

Wang J, Liu Y (2016) RVM-BASED urban hourly water consumption forecasting model and its application. J Simul 4:37

CAS   Google Scholar  

Wang C, Li Z, Ni X et al (2023) Residential water and energy consumption prediction at hourly resolution based on a hybrid machine learning approach. Water Res 246:120733. https://doi.org/10.1016/j.watres.2023.120733

Wei S, Xu T, Niu G-Y, Zeng R (2022) Estimating irrigation water consumption using machine learning and remote sensing data in Kansas high plains. Remote Sens 14:3004. https://doi.org/10.3390/rs14133004

Wong L-T, Mui K-W (2018) A review of demand models for water systems in buildings including a Bayesian approach. Water 10:1078. https://doi.org/10.3390/w10081078

Wu S, Han H, Hou B, Diao K (2020) Hybrid model for short-term water demand forecasting based on error correction using chaotic time series. Water 12:1683. https://doi.org/10.3390/w12061683

Xu TY, Qin XS (2015) A sequential fuzzy model with general-shaped parameters for water supply-demand analysis. Water Resour Manage 29:1431–1446. https://doi.org/10.1007/s11269-014-0884-8

Yang L, Feng Q, Lu T et al (2023) The response of agroecosystem water use efficiency to cropland change in northwest China’s Hexi Corridor. Agric Water Manag 276:108062. https://doi.org/10.1016/j.agwat.2022.108062

Yurdusev MA, Firat M (2009) Adaptive neuro fuzzy inference system approach for municipal water consumption modeling: an application to Izmir, Turkey. J Hydrol 365:225–234. https://doi.org/10.1016/j.jhydrol.2008.11.036

Zubaidi S, Al-Bugharbee H, Ortega-Martorell S et al (2020a) A novel methodology for prediction urban water demand by wavelet denoising and adaptive neuro-fuzzy inference system approach. Water 12:1628. https://doi.org/10.3390/w12061628

Zubaidi SL, Abdulkareem IH, Hashim KS et al (2020b) Hybridised artificial neural network model with slime mould algorithm: a novel methodology for prediction of urban stochastic water demand. Water 12:2692. https://doi.org/10.3390/w12102692

Zubaidi SL, Ortega-Martorell S, Al-Bugharbee H et al (2020c) Urban water demand prediction for a city that suffers from climate change and population growth: Gauteng province case study. Water 12:1885. https://doi.org/10.3390/w12071885

Download references

Acknowledgements

The authors are grateful to Ryan Nedd, Herbert Franklin, Ernesta Hunter, Walker Marechal, and Maxo Etienne for their feedback and support with editing.

This research was funded by the National Institute of Food and Agriculture of the United States Department of Agriculture (USDA-NIFA) to Florida A&M University through Non-Assistance Cooperative Agreement grant no. 58–6066-1–044. Additionally, support from the USDA-NIFA capacity-building grants 2017–38821-26405 and 2022–38821-37522, USDA-NIFA Evans-Allen Project, Grant 11979180/2016–01711, USDA-NIFA grant no. 2018–68002-27920, and the National Science Foundation Grant no. 1735235 was awarded as part of the National Science Foundation Research Traineeship and Grant no. 2123440.

Author information

Authors and affiliations.

School of the Environment, Florida Agricultural and Mechanical University, FSH Science Research Center, 1515 S. MLK Jr. BLVD, Tallahassee, FL, 32307, USA

Almando Morain

Woodbridge Academy Magnet School, 1 Convery Blvd, Woodbridge, NJ, 07095, USA

Nivedita Ilangovan

Sustainable Water Management RU, USDA-ARS Stoneville, Stoneville, MS, USA

Christopher Delhom

Biological Systems Engineering, Florida Agricultural and Mechanical University, Benjamin Bannekar Tech C, 1409 Wahnish Way, Tallahassee, FL, 32307, USA

Aavudai Anandhi

You can also search for this author in PubMed   Google Scholar

Contributions

Almando Morain and Aavudai Anandhi: Conceptualization, visualization, methodology. Aavudai Anandhi: Resources, supervision, project administration, and funding acquisition. Almando Morain and Nivedita Ilangovan: Data curation and writing, original draft preparation. Almando Morain and Aavudai Anandhi: Writing, review, and editing. All the authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Aavudai Anandhi .

Ethics declarations

 conflicts of interest.

The authors declare no conflicts of interest.

Additional information

Publisher's note.

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 19 KB)

Supplementary file2 (docx 3.27 mb), rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Morain, A., Ilangovan, N., Delhom, C. et al. Artificial Intelligence for Water Consumption Assessment: State of the Art Review. Water Resour Manage (2024). https://doi.org/10.1007/s11269-024-03823-x

Download citation

Received : 11 October 2023

Accepted : 12 March 2024

Published : 25 April 2024

DOI : https://doi.org/10.1007/s11269-024-03823-x

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

• PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework
• Machine learning applications
• Advantages, disadvantages, and challenges of artificial intelligence for water consumption
• Artificial intelligence
• Hybrid models
• Performance indexes
• Learnable parameters
• Smart water management
• Find a journal
• Publish with us
• Track your research