Forecasting monthly groundwater level fluctuations in coastal aquifers using hybrid Wavelet packet-Support vector regression

• Published in: Cogent engineering Vol. 2; no. 1; p. 999414
• Main Authors: Sujay Raghavendra, N., Deka, Paresh Chandra
• Format: Journal Article
• Language: English
• Published: Abingdon Cogent 31.12.2015; Taylor & Francis Ltd; Taylor & Francis Group
• Subjects: Algorithms; Aquifers; Comparative studies; Forecasting; Groundwater; Groundwater levels; groundwater systems; Kernel functions; Modelling; Optimization; Radial basis function; radial basis function (RBF); Rainfall; Regression analysis; Regression models; Statistical analysis; Support vector machines; Wavelet analysis; Wavelet packet-Support vector regression; Wavelet packets
• ISSN: 2331-1916; 2331-1916
• DOI: 10.1080/23311916.2014.999414

This research demonstrates the state-of-the-art capability of Wavelet packet analysis in improving the forecasting efficiency of Support vector regression (SVR) through the development of a novel hybrid Wavelet packet-Support vector regression (WP-SVR) model for forecasting monthly groundwater level fluctuations observed in three shallow unconfined coastal aquifers. The Sequential Minimal Optimization Algorithm-based SVR model is also employed for comparative study with WP-SVR model. The input variables used for modeling were monthly time series of total rainfall, average temperature, mean tide level, and past groundwater level observations recorded during the period 1996-2006 at three observation wells located near Mangalore, India. The Radial Basis function is employed as a kernel function during SVR modeling. Model parameters are calibrated using the first seven years of data, and the remaining three years data are used for model validation using various input combinations. The performance of both the SVR and WP-SVR models is assessed using different statistical indices. From the comparative result analysis of the developed models, it can be seen that WP-SVR model outperforms the classic SVR model in predicting groundwater levels at all the three well locations (e.g. NRMSE (WP-SVR)  = 7.14, NRMSE (SVR)  = 12.27; NSE (WP-SVR)  = 0.91, NSE (SVR)  = 0.8 during the test phase with respect to well location at Surathkal). Therefore, using the WP-SVR model is highly acceptable for modeling and forecasting of groundwater level fluctuations.