RESUMO
The estimation of groundwater levels is crucial and an important step in ensuring sustainable management of water resources. In this paper, selected piezometers of the Hamedan-Bahar plain located in west of Iran. The main objective of this study is to compare effect of various pre-processing methods on input data for different artificial intelligence (AI) models to predict groundwater levels (GWLs). The observed GWL, evaporation, precipitation, and temperature were used as input variables in the AI algorithms. Firstly, 126 method of data pre-processing was done by python programming which are classified into three classes: 1- statistical methods, 2- wavelet transform methods and 3- decomposition methods; later, various pre-processed data used by four types of widely used AI models with different kernels, which includes: Support Vector Machine (SVR), Artificial Neural Network (ANN), Long-Short Term memory (LSTM), and Pelican Optimization Algorithm (POA) - Artificial Neural Network (POA-ANN) are classified into three classes: 1- machine learning (SVR and ANN), 2- deep learning (LSTM) and 3- hybrid-ML (POA-ANN) models, to predict groundwater levels (GWLs). Akaike Information Criterion (AIC) were used to evaluate and validate the predictive accuracy of algorithms. According to the results, based on summation (train and test phases) of AIC value of 1778 models, average of AIC values for ML, DL, hybrid-ML classes, was decreased to -25.3%, -29.6% and -57.8%, respectively. Therefore, the results showed that all data pre-processing methods do not lead to improvement of prediction accuracy, and they should be selected very carefully by trial and error. In conclusion, wavelet-ANN model with daubechies 13 and 25 neurons (db13_ANN_25) is the best model to predict GWL that has -204.9 value for AIC which has grown by 5.23% (-194.7) compared to the state without any pre-processing method (ANN_Relu_25).
RESUMO
Predicting groundwater level (GWL) fluctuations, which act as a reserve water reservoir, particularly in arid and semi-arid climates, is vital in water resources management and planning. Within the scope of current research, a novel hybrid algorithm is proposed for estimating GWL values in the Tabriz plain of Iran by combining the artificial neural network (ANN) algorithm with newly developed nature-inspired Coot and Honey Badger metaheuristic optimization algorithms. Various combinations of meteorological data such as temperature, evaporation, and precipitation, previous GWL values, and the month and year values of the data were used to evaluate the algorithm's success. Furthermore, the Shannon entropy of model performance was assessed according to 44 different statistical indicators, classified into two classes: accuracy and error. Hence, based on the high value of Shannon entropy, the best statistical indicator was selected. The results of the best model and the best scenario were analyzed. Results indicated that value of Shannon entropy is higher for the accuracy class than error class. Also, for accuracy and error class, respectively, Akaike information criterion (AIC) and residual sum of squares (RSS) indexes with the highest entropy value which is equal to 12.72 and 7.3 are the best indicators of both classes, and Legate-McCabe efficiency (LME) and normalized root mean square error-mean (NRMSE-Mean) indexes with the lowest entropy value which is equal to 3.7 and - 8.3 are the worst indicators of both classes. According to the evaluation best indicator results in the testing phase, the AIC indicator value for HBA-ANN, COOT-ANN, and the standalone ANN models is equal to - 344, - 332.8, and - 175.8, respectively. Furthermore, it was revealed that the proposed metaheuristic algorithms significantly improve the performance of the standalone ANN model and offer satisfactory GWL prediction results. Finally, it was concluded that the Honey Badger optimization algorithm showed superior results than the Coot optimization algorithm in GWL prediction.
