Groundwater level modeling using multi-objective optimization hybridizing artificial intelligence

Abstract

Abstract Estimating groundwater level (GWL) fluctuations is essential for integrated water resource management in arid and semi-arid regions. This study promotes the multi-layer perceptron (MLP) learning process using hybrid evolutionary algorithms. This hybrid metaheuristic algorithm was applied to overcome MLP difficulties in the learning process, including its low conversions and local minimum. Also, the hybrid model benefits from the advantages of two objective function procedures in finding MLP parameters that result in a robust model regardless of over and under-estimating problems. These algorithms include none dominated sorting genetic algorithm (NSGA II) and multi-objective particle swarm optimisation (MOPSO) in different patterns, including MLP–NSGA-II, MLP–MOPSO, MLP-MOPSO–NSGA-II, and MLP-2NSGA-II–MOPSO. Temperature, precipitation and GWL datasets were used in various combinations and delays as model input candidates. Finally, the best model inputs were selected using the correlation coefficient (R2). Input parameters include temperature and precipitation delays of 3, 6, and 9 months and GWL delays of 1 to 12 months. In the next step, the performance of the different combinations of MLP and hybrid evolutionary algorithms was evaluated using The root mean square error (RMSE), correlation coefficient (R), and mean absolute error (MAE) indices. The outcomes of these evaluations revealed that the MLP-2NSGA-II-MOPSO model, with an RMSE=0.073, R=0.98, and MAE=0.059, outperforms other models in estimating GWL fluctuations. The selected model benefits from the advantages of both MOPSO and NSGA-II regarding accuracy and speed. The results also indicated the superiority of multi-objective optimization algorithms in promoting MLP performance.