Comparative Analysis of ANN and SVM Models Combined with Wavelet Preprocess for Groundwater Depth Prediction

Abstract

Reliable prediction of groundwater depth fluctuations has been an important component in sustainable water resources management. In this study, a data-driven prediction model combining discrete wavelet transform (DWT) preprocess and support vector machine (SVM) was proposed for groundwater depth forecasting. Regular artificial neural networks (ANN), regular SVM, and wavelet preprocessed artificial neural networks (WANN) models were also developed for comparison. These methods were applied to the monthly groundwater depth records over a period of 37 years from ten wells in the Mengcheng County, China. Relative absolute error (RAE), Pearson correlation coefficient (r), root mean square error (RMSE), and Nash-Sutcliffe efficiency (NSE) were adopted for model evaluation. The results indicate that wavelet preprocess extremely improved the training and test performance of ANN and SVM models. The WSVM model provided the most precise and reliable groundwater depth prediction compared with ANN, SVM, and WSVM models. The criterion of RAE, r, RMSE, and NSE values for proposed WSVM model are 0.20, 0.97, 0.18 and 0.94, respectively. Comprehensive comparisons and discussion revealed that wavelet preprocess extremely improves the prediction precision and reliability for both SVM and ANN models. The prediction result of SVM model is superior to ANN model in generalization ability and precision. Nevertheless, the performance of WANN is superior to SVM model, which further validates the power of data preprocess in data-driven prediction models. Finally, the optimal model, WSVM, is discussed by comparing its subseries performances as well as model performance stability, revealing the efficiency and universality of WSVM model in data driven prediction field.

Wavelet-ANN versus ANN-Based Model for Hydrometeorological Drought Forecasting

“…In the last decade, wavelet transform has become a widely applied technique for analyzing variations, periodicities, and trends in time series [20,21]. Wavelet transform, which can produce a good local representation of the signal, in both the time and frequency domains, provides considerable information on the structure of the physical process to be modelled.…”

Spatiotemporal Patterns of Extreme Temperature across the Huai River Basin, China, during 1961–2014, and Regional Responses to Global Changes

“…Besides, variations of temperature have affected the lengths of growing season in both space and time, which have substantial implications for agricultural activities [31]. However, few reports were found pertaining to investigations of extreme temperature regimes across the Huai River Basin [32][33][34]. The objective of this study is to dissect the changes in extreme temperatures with a complete picture of temperature indices, and to quantify the correlations between growing season length and temperature changes.…”

“…Besides, variations of temperature have affected the lengths of growing season in both space and time, which have substantial implications for agricultural activities [31]. However, few reports were found pertaining to investigations of extreme temperature regimes across the Huai River Basin [32][33][34]. China is the largest agricultural country with the largest population in the world [24][25][26].…”

Probability Analysis of the Water Table and Driving Factors Using a Multidimensional Copula Function

“…Reliable prediction methods of the water table play significant roles in terms of groundwater planning and comprehensive management [2]. Over the years, scholars have applied different methods to study the water table, including the Linear Regression Method [3,4], Clustering Method [5], ARIMA Model [6], Genetic Programming Method, Neutral Network Method [7], Wavelet Approach [8], and SVM (Support Vector Machine) method [9], as well as the joint application of several methods [10,11].…”