Using machine learning algorithms to map the groundwater recharge potential zones

Hamid Reza Pourghasemi; Nitheshnirmal Sadhasivam; Saleh Yousefi; Shahla Tavangar; Hamid Ghaffari Nazarlou; M Santosh

doi:10.1016/j.jenvman.2020.110525

Using machine learning algorithms to map the groundwater recharge potential zones

J Environ Manage. 2020 Jul 1:265:110525. doi: 10.1016/j.jenvman.2020.110525. Epub 2020 Apr 7.

Authors

Hamid Reza Pourghasemi¹, Nitheshnirmal Sadhasivam², Saleh Yousefi³, Shahla Tavangar⁴, Hamid Ghaffari Nazarlou⁵, M Santosh⁶

Affiliations

¹ Department of Natural Resources and Environmental Engineering, College of Agriculture, Shiraz University, Shiraz, Iran. Electronic address: hr.pourghasemi@shirazu.ac.ir.
² Department of Geography, School of Earth Science, Bharathidasan University, Tiruchirappalli, 620 024, Tamil Nadu, India.
³ Soil Conservation and Watershed Management Research Department, Chaharmahal and Bakhtiari Agricultural and Natural Resources Research and Education Center, AREEO, Shahrekord, Iran.
⁴ Department of Watershed Management Engineering, Faculty of Natural Resources and Marine Sciences, Tarbiat Modare University, Iran.
⁵ Department of Civil and Environmental Engineering, Howard University, Washington DC, USA.
⁶ School of Earth Sciences and Resources, China University of Geosciences Beijing, Beijing, 100083, PR China; Department of Earth Sciences, University of Adelaide, Adelaide, SA, 5005, Australia.

PMID: 32275245
DOI: 10.1016/j.jenvman.2020.110525

Abstract

Groundwater recharge is indispensable for the sustainable management of freshwater resources, especially in the arid regions. Here we address some of the important aspects of groundwater recharge through machine learning algorithms (MLAs). Three MLAs including, SVM, MARS, and RF were validated for higher prediction accuracies in generating groundwater recharge potential maps (GRPMs). Accordingly, soil permeability samples were prepared and are arbitrarily grouped into training (70%) and validation (30%) samples. The GRPMs are generated using sixteen effective factors, such as elevation (denoted using a digital elevation model; DEM), aspect, slope angle, TWI (topographic wetness index), fault density, MRVBF (multiresolution index of valley bottom flatness), rainfall, lithology, land use, drainage density, distance from rivers, distance from faults, annual ETP (evapo-transpiration), minimum temperature, maximum temperature, and rainfall 24-hr. Subsequently, the VI (variables importance) is assessed based on the LASSO algorithm. The GRPMs of three MLAs were validated using the ROC-AUC (receiver operating characteristic-area under curve) and various techniques including true positive rate (TPR), false positive rate (FPR), F-measures, fallout, sensitivity, specificity, true skill statistics (TSS), and corrected classified instances (CCI). Based on the validation, the RF algorithm performed better (AUC = 0.987) than the SVM (AUC = 0.963) and the MARS algorithm (AUC = 0.962). Furthermore, the accuracy of these MLAs are included in excellent class, based on the ROC curve threshold. Our case study shows that the GRPMs are potential guidelines for decision-makers in drafting policies related to the sustainable management of the groundwater resources.

Keywords: Groundwater recharge; LASSO; Machine learning algorithms; Variable importance.

MeSH terms

Algorithms
Environmental Monitoring*
Groundwater*
Machine Learning
Rivers