Water Resources Management

, Volume 32, Issue 2, pp 401–416 | Cite as

A Two-stage Approach to Basin-scale Water Demand Prediction

  • Yanhu He
  • Jie Yang
  • Xiaohong Chen
  • Kairong Lin
  • Yanhui Zheng
  • Zhaoli Wang


Water demand prediction (WDP) is the basis for water allocation. However, traditional methods in WDP, such as statistical modeling, system dynamics modeling, and the water quota method have a critical disadvantage in that they do not consider any constraints, such as available water resources and ecological water demand. This study proposes a two-stage approach to basin-scale WDP under the constraints of total water use and ecological WD, aiming to flexibly respond to a dynamic environment. The prediction method was divided into two stages: (i) stage 1, which is the prediction of the constrained total WD of the whole basin (T w ) under the constraints of available water resources and total water use quota released by the local government and (ii) stage 2, which is the allocation of T w to its subregions by applying game theory. The WD of each subregion (T s ) was predicted by calculating its weight based on selected indicators that cover regional socio-economic development and water use for different industries. The proposed approach was applied in the Dongjiang River (DjR) basin in South China. According to its constrained total water use quota and ecological WD, T w data were 7.92, 7.3, and 5.96 billion m3 at the precipitation frequencies of 50%, 90%, and 95%, respectively (in stage 1). Industrial WDs in the domestic, primary, secondary, tertiary, and environment sectors are 1.08, 2.26, 2.02, 0.44, and 0.16 billion m3, respectively, in extreme dry years (in stage 2). T w and T s exhibit structures similar to that of observed water use, mainly in the upstream and midstream regions. A larger difference is observed between T s and its total observed water use, owing to some uncertainties in calculating T w . This study provides useful insights into adaptive basin-scale water allocation under climate change and the strict policy of water resource management.


Water demand prediction Two-stage approach Game theory Dongjiang River basin, South China 



The authors would like to express their gratitude to all of the reviewers for their valuable recommendations. This study was financially supported by the National Natural Science Foundation of China (Grant No.: Grant No.: 51509127, 91547202, 51210013, 51479216, 51569009 and 91547108).


  1. 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(10):729–743CrossRefGoogle Scholar
  2. Adamowski J, Chan HF, Prasher SO, Ozga-Zielinski B, Sliusarieva A (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 Resour Res 48(1):273–279CrossRefGoogle Scholar
  3. Al-Zahrani M, Abo-Monasar A (2015) Urban residential water demand prediction based on artificial neural networks and time series models. Water Resour Manag 236:3651–3662CrossRefGoogle Scholar
  4. Babel MS, Maporn N, Shinde VR (2014) Incorporating future climatic and socioeconomic variables in water demand forecasting: a case study in Bangkok. Water Resour Manag 28(7):2049–2062CrossRefGoogle Scholar
  5. Bai Y, Wang P, Li C, Xie J, Wang Y (2014) A multi-scale relevance vector regression approach for daily urban water demand forecasting. J Hydrol 517:236–245CrossRefGoogle Scholar
  6. Campisi-Pinto S, Adamowski J, Oron G (2012) Forecasting urban water demand via wavelet-denoising and neural network models. Case study: city of Syracuse. Italy Water Resour Manage 26(12):3539–3558CrossRefGoogle Scholar
  7. Chen KY (2011) Combining linear and nonlinear model in forecasting tourism demand. Expert Syst Appl 38(8):10368–10376CrossRefGoogle Scholar
  8. Chen J, Boccelli DL (2014) Demand forecasting for water distribution systems. Procedia Engineering 70:339–342CrossRefGoogle Scholar
  9. De A Lima Neto E, de A. T. de Carvalho F, Freire ES (2005) Applying constrained linear regression models to predict interval-valued data. In Annual Conference on artificial intelligence, Springer Berlin Heidelberg, pp 92–106Google Scholar
  10. Elliott J, Deryng D, Müller C, Frieler K, Konzmann M, Gerten D, Eisner S (2014) Constraints and potentials of future irrigation water availability on agricultural production under climate change. Proc Natl Acad Sci 111(9):3239–3244CrossRefGoogle Scholar
  11. Firat M, Turan ME, Yurdusev MA (2009) Comparative analysis of fuzzy inference systems for water consumption time series prediction. J Hydrol 374:235–241CrossRefGoogle Scholar
  12. Ghimire M, Boyer TA, Chung C, Moss JQ (2016) Estimation of residential water demand under uniform volumetric water pricing. J Water Resour Plann Manag 142(2):04015054CrossRefGoogle Scholar
  13. Guangdong Provincial Water Resources Department (2012) Control target for total water use of Guangdong province,Guangzhou, pp 8–10Google Scholar
  14. He YH, Lin KR, Chen XH (2013) Effect of land use and climate change on runoff in the Dongjiang Basin of South China. Math Probl Eng.
  15. He YH, Lin KR, Chen XH, Ye CQ, Cheng L (2015) Classification-based spatiotemporal variations of pan evaporation across the Guangdong Province, South China. Water Resour Manag 29:901–912CrossRefGoogle Scholar
  16. Li N, Wang XJ, Shi MJ, Hong Y (2015) Economic impacts of Total water use control in the Heihe River basin in Northwestern China-an integrated CGE-BEM modeling approach. Sustain For 7:3460–3478CrossRefGoogle Scholar
  17. Lin KR, Lian YQ, Chen XH, Lu F (2014a) Changes in runoff and eco-flow in the Dongjiang River of the Pearl River basin. China Front Earth Sci.
  18. Lin KR, Lv FS, Lu C, Singh VP, Zhang Q, Chen XH (2014b) Xinanjiang model combined with curve number to simulate the effect of land use change on environmental flow. J Hydrol 519:3142–3315CrossRefGoogle Scholar
  19. Liu CM, Wang HR (2003) An analysis of the relationship between water resources and population-economy-society-environment. Journal of Natural Resources 18(5):635–644Google Scholar
  20. Mastorocostas PA, Theocharis JB, Petridis VS (2001) A constrained orthogonal least-squares method for generating TSK fuzzy models: application to short-term load forecasting. Fuzzy Sets Syst 118(2):215–233CrossRefGoogle Scholar
  21. Mohtar RH, Daher B (2016) Water-energy-food nexus framework for facilitating multi-stakeholder dialogue. Water Int 41(5):655–661Google Scholar
  22. Mombeni HA, Rezaei S, Nadarajah S, Emami M (2013) Estimation of water demand in Iran based on SARIMA models. Environ Model Assess 18(5):559–565CrossRefGoogle Scholar
  23. Mouatadid S, Adamowski J (2016) Using extreme learning machines for short-term urban water demand forecasting. Urban Water J 14(6):630–638Google Scholar
  24. Pathak D, Krahenbuhl P, Darrell T (2015) Constrained convolutional neural networks for weakly supervised segmentation. IEEE Int Conf Comput Vis 1–12. Cite as:arXiv:1506.03648Google Scholar
  25. Qin Y, Curmi E, Kopec GM, Allwood JM, Richards KS (2015) China's energy-water nexus – assessment of the energy sector's compliance with the “3 red lines” industrial water policy. Energ Policy 82(1):131–143CrossRefGoogle Scholar
  26. Rinaudo J-D (2015) Long-term water demand forecasting. Understanding and Managing Urban Water in Transition. Springer, Netherlands, pp 239–268CrossRefGoogle Scholar
  27. Romano M, Kapelan Z (2014) Adaptive water demand forecasting for near real-time management of smart water distribution systems. Environ Model Softw 60:265–275CrossRefGoogle Scholar
  28. Wada Y, Wisser D, Eisner S, Flörke M, Gerten D, Haddeland I, Tessler Z (2013) Multimodel projections and uncertainties of irrigation water demand under climate change. Geophys Res Lett 40(17):4626–4632CrossRefGoogle Scholar
  29. Wang XJ, Zhang JY, Shahid S, Guan EH, Wu YX, Gao J, He RM (2016) Adaptation to climate change impacts on water demand. Mitig Adapt Strateg Glob Chang 21(1):81–99CrossRefGoogle Scholar
  30. Yang LE, Chan FS, Scheffran J (2016) Climate change, water management and stakeholder analysis in the Dongjiang River basin in South China. Int J Water Resour Dev.
  31. Zhai Y, Wang J, Teng Y, Zuo R (2012) Water demand forecasting of Beijing using the time series forecasting method. J Geogr Sci 22(5):919–932CrossRefGoogle Scholar
  32. Zhang Q, Cui Y, Chen YQ (2012) Ecological flow evaluation based on hydrological alterations in the Dongjiang River basin. J Nat Resour 27(5):790–800Google Scholar
  33. Zhou SL, McMahon TA, Walton A, Lewis J (2000) Forecasting daily urban water demand: a case study of Melbourne. J Hydrol 236:153–164CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2017

Authors and Affiliations

  • Yanhu He
    • 1
  • Jie Yang
    • 1
  • Xiaohong Chen
    • 1
  • Kairong Lin
    • 1
  • Yanhui Zheng
    • 1
  • Zhaoli Wang
    • 2
  1. 1.Department of Water Resources and EnvironmentSunYat-sen UniversityGuangzhouChina
  2. 2.School of Civil Engineering and TransportationSouth China University of TechnologyGuangzhouChina

Personalised recommendations