Development of hybrid models to forecast water demand in the city of Ankara

UZLU E., DEDE T.

Soft Computing, cilt.29, sa.17-18, ss.5401-5414, 2025 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 29 Sayı: 17-18
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1007/s00500-025-10904-5
  • Dergi Adı: Soft Computing
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC, zbMATH
  • Sayfa Sayıları: ss.5401-5414
  • Anahtar Kelimeler: GWO algorithm, Jaya algorithm, Neural networks, Water demand forecasting
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

Realistic water consumption projections are of vital importance for efficient use of water resources and for the prevention of water waste and scarcity. In this study, estimates of future water consumption in Ankara, Turkey were developed based on gross domestic product (GDP) and population data from the 22-year period of 2000‒2021. Artificial neural networks (ANNs) were trained with back-propagation (BP), Jaya, and grey wolf optimization (GWO) algorithms, yielding ANN-BP, ANN-Jaya, and ANN-GWO models, respectively. ANN performance evaluation based on calculation of errors for training and test datasets indicated that the ANN-Jaya model showed superior performance compared to the ANN-BP and ANN-GWO models. Therefore, the ANN-Jaya model was used to estimate Ankara’s annual water demand values ​for the 29-year period of 2025‒2054 for three different scenarios and compared with official estimates. The estimates obtained in this study for high- and low-demand scenarios are 28.95% and 42.45% higher than current official estimates, respectively. Official water demand projections should thus be re-evaluated to prevent water shortages in Ankara. Notably, if a drought similar to that which occurred between 2004 and 2009 occurs in Ankara within the coming decade, the present findings indicate that existing resources will not be sufficient to meet the city’s water needs after the year 2035.