Modeling and Uncertainty Analysis of Groundwater Level Using Six Evolutionary Optimization Algorithms Hybridized with ANFIS, SVM, and ANN

Abstract

In the present study, six meta-heuristic schemes are hybridized with artificial neural network (ANN), adaptive neuro-fuzzy interface system (ANFIS), and support vector machine (SVM), to predict monthly groundwater level (GWL), evaluate uncertainty analysis of predictions and spatial variation analysis. The six schemes, including grasshopper optimization algorithm (GOA), cat swarm optimization (CSO), weed algorithm (WA), genetic algorithm (GA), krill algorithm (KA), and particle swarm optimization (PSO), were used to hybridize for improving the performance of ANN, SVM, and ANFIS models. Groundwater level (GWL) data of Ardebil plain (Iran) for a period of 144 months were selected to evaluate the hybrid models. The pre-processing technique of principal component analysis (PCA) was applied to reduce input combinations from monthly time series up to 12-month prediction intervals. The results showed that the ANFIS-GOA was superior to the other hybrid models for predicting GWL in the first piezometer (RMSE:1.21, MAE:0.878, NSE:0.93, PBIAS:0.15, R2:0.93), second piezometer (RMSE:1.22, MAE:0.881, NSE:0.92, PBIAS:0.17, R2:0.94), and third piezometer (RMSE:1.23, MAE:0.911, NSE:0.91, PBIAS:0.19, R2:0.94) in the testing stage. The performance of hybrid models with optimization algorithms was far better than that of classical ANN, ANFIS, and SVM models without hybridization. The percent of improvements in the ANFIS-GOA versus standalone ANFIS in piezometer 10 were 14.4%, 3%, 17.8%, and 181% for RMSE, MAE, NSE, and PBIAS in training stage and 40.7%, 55%, 25%, and 132% in testing stage, respectively. The improvements for piezometer 6 in train step were 15%, 4%, 13%, and 208% and in test step were 33%, 44.6%, 16.3%, and 173%, respectively, that clearly confirm the superiority of developed hybridization schemes in GWL modelling. Uncertainty analysis showed that ANFIS-GOA and SVM had, respectively, the best and worst performances among other models. In general, GOA enhanced the accuracy of the ANFIS, ANN, and SVM models.

Evaluating the Impacts of Pumping on Aquifer Depletion in Arid Regions Using MODFLOW, ANFIS and ANN

“…The average of the weighted output of each rule becomes the concluding output. The functional block of ANFIS, consisting of fuzzification, inference, and defuzzification processes, is presented in Figure 6b [30,31].…”

“…Recently, Gao et al [29] used GRU for solving a similar problem in Luoyang, China. Although the application of these deep learning arterial intelligence models in the field of groundwater predictions is relatively rare to date, some researchers used the ANN, ANFIS, and SVR to simulate groundwater-levels [30][31][32][33][34][35][36]. The modeling of aquifers becomes highly challenging if the boundary conditions are not well defined for their certain parts.…”

Optimization of induced voltage on a buried pipeline from HV power lines using grasshopper algorithm (GOA)

“…All tests have completed under the same conditions and parameters values. Generally, for the training/testing methodology, the data set is divided into training set (80%) and testing set (20%) [14,39,[42][43][44][45][46]. DIAGNOSTYKA, Vol.…”

Prediction Interval Estimation Methods for Artificial Neural Network (ANN)-Based Modeling of the Hydro-Climatic Processes, a Review

“…Seifi, Ehteram, Singh and Mosavi [59] attempted to evaluate the uncertainty of groundwater level modeling via the hybrid ANN modeling and some other black box models and six meta-heuristic optimization methods, such as the grasshopper algorithm, cat swarm, weed algorithm, genetic algorithm, krill algorithm and particle swarm optimization, and it was mentioned that hybrid methods led to better performance and accuracy than sole methods.…”