Spatial mapping of groundwater springs potentiality using grid search-based and genetic algorithm-based support vector regression

• Published in: Geocarto international Vol. 37; no. 1; pp. 284 - 303
• Main Authors: Al-Fugara, A'kif, Ahmadlou, Mohammad, Al-Shabeeb, Abdel Rahman, AlAyyash, Saad, Al-Amoush, Hani, Al-Adamat, Rida
• Format: Journal Article
• Language: English
• Published: Taylor & Francis 30.01.2022
• Subjects: algorithms; altitude; drainage; genetic algorithm; grid searching; groundwater; Groundwater potential mapping; land use; lithology; mapping; normalized difference vegetation index; regression analysis; springs (water); streams; support vector regression
• ISSN: 1010-6049; 1752-0762; 1752-0762
• DOI: 10.1080/10106049.2020.1716396

In this study, groundwater springs potentiality maps were prepared using a novel integrated model, support vector regression (SVR) with genetic algorithm (GA), for the Jerash and Ajloun region, Jordan.The conditioning factors such as altitude, aspect, slope angle, plan curvature, stream power index, topographic wetness index, length of slope, distance from drainage network, lithology, distance from faults, land use and normalised difference vegetation index were considered to map the groundwater spring potentiality. GA was used for two purposes. First, GA was used to optimize the hyper-parameters of the radial basis function (RBF) kernel of SVR model. Second, GA in combination with SVR was used as feature selection (FS).The results of these models were compared with common grid search (GS) method used in most of the studies. The GS method was employed to calculate the parameters related to the SVR model and also hyper-parameters of RBF kernel. The results show optimum values of the kernels in the SVR model and selecting the optimal features which have the most contribution in modeling were the major steps in modeling and also in achieving a desirable precision level.