Development of adaptive neuro fuzzy inference system –Evolutionary algorithms hybrid models (ANFIS-EA) for prediction of optimal groundwater exploitation

• Published in: Journal of hydrology (Amsterdam) Vol. 598; p. 126258
• Main Authors: Ghordoyee Milan, Sami, Roozbahani, Abbas, Arya Azar, Naser, Javadi, Saman
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.07.2021
• Subjects: algorithms; ANFIS; ANFIS-GWO; ANFIS-HHO; ANFIS-PSO; aquifers; Conjunctive Use; cost effectiveness; fuzzy logic; groundwater; groundwater extraction; Groundwater Management; Iran; prediction; surface water; Iran; Conjunctive Use; ANFIS; ANFIS-PSO; ANFIS-GWO; ANFIS-HHO; Groundwater Management
• ISSN: 0022-1694; 1879-2707
• DOI: 10.1016/j.jhydrol.2021.126258

•The approach for optimal extracting of groundwater resources is developed.•A novel insight on forecasting OGE is developed by hybridizing ANFIS and EA algorithms.•ANFIS-HHO, ANFIS-GWO and ANFIS-PSO models improve the predictive precision of OGE.•The results show that ANFIS-HHO is superior for groundwater management in study area. The present study deals with the optimal extraction of groundwater resources. This approach has been developed for optimal integrated operation in an aquifer in Iran. The results of simulation / optimization models have been used to develop a predictive model based on machine learning. In the first stage, adaptive neuro-fuzzy inference system (ANFIS) was used to predict the Optimal Groundwater Exploitation (OGE) amount in each month having the amounts of several inputs, including the drop and amount of surface water at the end of the previous month and two months earlier, and the water demand of the current month. The results showed that the model’s performance in predicting the test data was undesirable. Therefore, to improve the prediction results, in the second stage several evolutionary optimization algorithms, i.e., particle swarm optimization (PSO), gray wolf optimization (GWO), and Harris hawk optimization (HHO), were used to train ANFIS model. The results indicated the appropriate performance of HHO in ANFIS training, which significantly improved the prediction accuracy of this model. The best scenario for the ANFIS-HHO model included all the input parameters, which resulted in RMSE = 1.45, MAE = 1.15, and R2 = 0.99 respectively, for the test data. In addition, the Taylor diagram (RMSD = 1.40, STD = 15.5 and CC = 0.99) showed ANFIS-HHO accuracy in estimating the OGE value. ANFIS-HHO was also able to improve the accuracy of anfis by RMSE = 4 and MAE = 2 MCM. In general, ANFIS-POS, ANFIS-GWO and ANFIS-HHO had good predictive accuracy compared to ANFIS. The results assure the authors to suggest the developed approach to experts for timely and cost-effective prediction of OGE in similar study areas.