Document Type : Original Article

Authors

• ebrahim nohani ¹
• hamidreza babaali ²
• reza dehghani ³

¹ Assistant Professor, Department of Civil Engineering, Materials and Energy Research Center, Dezful Branch, Islamic Azad University, Dezful, Iran.

² Associate Professor, Department of Civil Engineering, Azad University, Khorramabad Branch, Khorramabad, Iran

³ PhD in Water Sciences and Engineering, Department of Soil Conservation and Watershed Management, Lorestan Province Agriculture and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization, Khorramab

Abstract

Groundwater plays a crucial role in supplying freshwater, especially in arid and semi-arid regions. This study presents a novel and accurate approach for predicting groundwater level. The metaheuristic algorithms, namely, whale optimization algorithm (WOA), particle swarm optimization (PSO), and wavelet optimization algorithm (WV) are used to train the artificial neural network (ANN) model for predicting groundwater level. In this study, a dataset consisting of 20 wells and Piezometric observations from Delfan Plain, Lorestan province, is used for training and testing of the proposed models. The performance of the models is evaluated using statistical metrics, including coefficient of correlation ®, root mean square error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe efficiency (NSE). The results indicate that the hybrid models outperform the traditional models in terms of prediction accuracy. The ANN-WV model exhibits the best performance among the developed models, with R = 0.976, RMSE = 0.341, MAE = 0.267, and NSE = 0.956. The results of this study demonstrate the potential of metaheuristic optimization algorithms in improving the accuracy of groundwater level prediction models.

Keywords

• Groundwater level
• Artificial neural network
• Metaheuristic optimization
• Delfan plain

Main Subjects

• ًQanat and aquifer