Volume 26, Issue 4 (Winiter 2023)
jwss 2023, 26(4): 281-297 |
Back to browse issues page
University of Tehran , EbrahimiK@ut.ac.ir
Abstract: (1250 Views)
In this study, the accuracy of the Adaptive Network-Based Fuzzy Inference System (ANFIS) in integrating with the Gray Wolf Algorithm (ANFIS-GWO) in predicting groundwater level was evaluated for the first time using unpublished observational data from 1998 to 2018 in the Zarandieh aquifer, central Iran. Three observational wells were randomly selected for analysis. Assessment of evaluation criteria demonstrated that among the proposed scenarios using the hybrid model, the D scenario was selected as the optimal scenario with input data including the previous month's groundwater level, precipitation, temperature, and groundwater extraction. In the D scenario, parameters including MAPE, RMSE, and NASH were 0.29 m, 0.47 m, and 0.99, respectively for the first observational well. Also, C scenario with input data including the previous month's groundwater level, precipitation, and groundwater extraction for the second observational well, for the same parameters mentioned above equal to 0.20 m, 0.26 m, and 0.99. As well for the third observational well, the A scenario with input data including the previous month's groundwater level for the same parameters equal to 0.29 m, 0.41 m, and 0.99 as the optimal scenarios were selected using the ANFIS-GWO model. Based on the results, the Gray wolf algorithm in training the ANFIS model was able to reduce the average forecast error by equal to 0.03 (RMSE) and 0.02 (MAPE) meter and increased the average NASH value equal to 0.01 and increased the accuracy of predictions.
Keywords: Groundwater, Sustainability of water resources, Fuzzy-adaptive neural inference system, Simulation, Intelligent model
Type of Study: Research |
Subject:
Ggeneral
Received: 2021/11/13 | Accepted: 2022/07/27 | Published: 2023/03/1
Received: 2021/11/13 | Accepted: 2022/07/27 | Published: 2023/03/1
| Rights and permissions | |
 | This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |