Stochastic artificial intelligence models for water resources management: innovative riverflow estimation amidst uncertainty

Abstract

Rivers provide irreplaceable resources for human life, and the problem of water scarcity has attracted serious attention worldwide. In this study, Kashkan River located in Loristan Province of Iran was studied using data obtained from the database of Iran Water Resources Company (IWRC). Three distinct machine learning (ML) models – Regression Tree (RT), Random Search Regression Tree (RSRT), and Bayesian Optimization Regression Tree (BORT) – were utilized to enhance water resource management practices. The primary model used was RT, a method that uses Bayesian optimization and stochastic search algorithms to provide an accurate estimate of the maximum flow within a river. The two hybrid models, RSRT and BORT, were introduced to improve the model performance. Through a comprehensive comparison and analysis of the results generated by these models, valuable insights were gained. Among the three models, the RSRT model demonstrated superior performance and accuracy metrics in streamflow (SF) modeling, closely aligning its results with a DR line of 1, indicating an optimal fit. The BORT and RT models also achieved excellent results, with their performance being on par with that of the top-performing RSRT model.

Keywords

Water resources management / Machine learning / Regression tree / Bayesian optimization / Random search optimization / River flow

References

[1] AydinMC, GelberiG, UluAE. Investigation of recent level changes in Lake Van using water balance, LSTM and ANN approaches. Applied Water Science, 2024, 14: 1-15.

[2] AziziE, YosefvandF, YaghoubiB, et al.. Modelling and prediction of groundwater level using wavelet transform and machine learning methods: A case study for the Sahneh Plain Iran. Irrig Drain, 2023, 72: 747-762.

[3] BhasmeP, BhatiaU. Improving the interpretability and predictive power of hydrological models: Applications for daily streamflow in managed and unmanaged catchments. Journal of Hydrology, 2024, 628. 130421

[4] FallahiMM, ShabanlouS, RajabiA, et al.. Effects of climate change on groundwater level variations affected by uncertainty (case study: Razan aquifer). Applied Water Science, 2023, 13: 1-16.

[5] HancockT, SmythC. Tree-based clustering and extensions. Comprehensive chemometrics, 2009Elsevier.

[6] JeihouniM, ToomanianA, MansourianA. Decision tree-based data mining and rule induction for identifying high quality groundwater zones to water supply management: A novel hybrid use of data mining and GIS. Water Resour Manag, 2020, 34: 139-154.

[7] KimG-B, HwangC-I, Kim Jihye. Estimation of groundwater recharge rates in small watersheds using regression tree model. Geosciences Journal, 2025, 2025: 1-17.

[8] LiangJ, DuY, XuY, et al.. Using adaptive chaotic grey wolf optimization for the daily streamflow prediction. Expert Systems with Applications, 2024, 237. 121113

[9] LinY, WangD, ZhuJ, et al.. Development of objective function-based ensemble model for streamflow forecasts. Journal of Hydrology, 2024, 632. 130861

[10] ManuDS, ThallaAK. Artificial intelligence models for predicting the performance of biological wastewater treatment plant in the removal of Kjeldahl Nitrogen from wastewater. Applied Water Science, 2017, 7: 3783-3791.

[11] MohammedKS, ShabanlouS, RajabiA, et al.. Prediction of groundwater level fluctuations using artificial intelligence-based models and GMS. Applied Water Science, 2023, 1354.

[12] NayakS. Multivariable constrained nonlinear optimization. Fundamentals of optimization techniques with algorithms, 2020Academic Press.

[13] NiaES, AsadollahfardiG, HeidarzadehN. Study of the environmental flow of rivers, a case study, Kashkan River Iran. J Water Supply Res Technol, 2016, 65: 181-194.

[14] PoursaeidM. An optimized extreme learning machine by evolutionary computation for river flow prediction and simulation of water pollution in Colorado River Basin, USA. Expert Systems with Applications, 2023, 233. 120998

[15] PoursaeidM. Modeling of wetlands storage instabilities using an optimized slffn machine learning using evolutionary computation considering the RROC analysis and PDF techniques. Earth Sci Informatics, 2024, 2024: 1-12.

[16] PoursaeidM. Comprehensive water quality indicators modeling by environmental protection view using multi optimized weighted ensemble machine learnings. Process Safety and Environment Protection, 2025, 193: 696-709.

[17] PoursaeidM. Unraveling the water quality-ecosystem nexus using Kalman filter-driven models and feature analysis under uncertainty. Journal of Hydrology, 2025, 657. 133092

[18] PoursaeidM. Optimizing transient monitoring of river streamflow by a highly predictive model utilizing Ensemble learning models and Multi algorithms. Journal of Hydrology, 2025, 647. 132373

[19] PoursaeidM, MastouriR, ShabanlouS, NajarchiM. Estimation of quantity and quality parameters of groundwater using numerical models (Case Study: Mighan Desert Basin, Arak). Iran J Soil Water Res, 2020, 51: 201-216.

[20] PoursaeidM, PoursaeedAH. A new strategy for prediction of water qualitative and quantitative parameters by deep learning-based models with determination of modelling uncertainties. Hydrological Sciences Journal, 2024, 69: 207-225.

[21] PoursaeidM, PoursaeedAH, ShabanlouS. Water quality fluctuations prediction and Debi estimation based on stochastic optimized weighted ensemble learning machine. Process Safety and Environment Protection, 2024, 188: 1160-1174.

[22] PoursaeidM, PoursaeedAH, ShabanlouS. Water resources quality indicators monitoring by nonlinear programming and simulated annealing optimization with ensemble learning approaches. Water Resour Manag, 2024.

[23] PoursaeidM, PoursaeidA, ShabanlouS. Hydraulic Modeling of the Water Resources using Learning Techniques. Iran J Soil Water Res, 2022, 52: 2739-2750

[24] PraseejaAV, YounusS. Monitoring of ground water level fluctuation in Chittur Palakkad. Int J Energy Water Resour, 2024.

[25] Rasiya KoyaS, RoyT. Temporal fusion transformers for streamflow prediction: Value of combining attention with recurrence. Journal of Hydrology, 2024, 637. 131301

[26] RehamniaI, Mahdavi-MeymandA. Advancing reservoir water level predictions: evaluating conventional ensemble and integrated swarm machine learning approaches. Water Resour Manag, 2024.

[27] SamaniS, VadiatiM, AziziF, et al.. Groundwater level simulation using soft computing methods with emphasis on major meteorological components. Water Resour Manag, 2022, 36: 3627-3647.

[28] SigaudO, StulpF. Policy search in continuous action domains: An overview. Neural Networks, 2019, 113: 28-40.

[29] Takai EddineY, NadirM, SabahS, JaafariA. Integrating support vector machines with different ensemble learners for improving streamflow simulation in an ungauged watershed. Water Resour Manag, 2024, 38: 553-567.

[30] ZhangC, García MárquezFP, ZhangL. Artificial intelligence techniques and cloud computing for wind turbine pitch bearing fault detection. Non-destructive testing and condition monitoring techniques in wind energy, 2023Elsevier.

RIGHTS & PERMISSIONS

The Author(s)