Abstract
The aim of this research is to introduce a novel ensemble approach using Vise Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR), frequency ratio (FR), and random forest (RF) models for groundwater-potential mapping (GWPM) in Bastam watershed, Iran. This region suffers from freshwater shortages and the identification of new groundwater sites is a critical need. Remote sensing and geographic information system (GIS) were used to reduce time and financial costs of rapid assessment of groundwater resources. Seventeen physiographical, hydrological, and geological groundwater conditioning factors (GWCFs) were derived from a spatial geo-database. Groundwater data were gathered in field surveys and well-yield data were acquired from the Iranian Department of Water Resources Management for 89 locations with high yield potential values ≥ 11 m3 h−1. These data were mapped in a GIS. From these locations, 62 (70%) were randomly selected to be used for model training, and the remaining 27 (30%) were used for validation of the model. The relative weights of the GWCFs were determined with an RF model. For GWPM, 220 randomly selected points in the study area and their final weights were determined with the VIKOR model. A groundwater potential map was created by interpolating the values at these points using Kriging in GIS. Finally, the area under receiver operating characteristic (AUROC) curve was plotted for the groundwater potential map. The success rate curve (SRC) was computed for the training dataset, and the prediction rate curve (PRC) was calculated for the validation dataset. Results of RF analysis show that land use and land cover, lithology, and elevation are the most significant determinants of groundwater occurrence. The validation results show that the ensemble model had excellent prediction performance (PRC = 0.934) and goodness-of-fit (SRC = 0.925) and reasonably high classification accuracy. The results of this study could aid management of groundwater resources and assist planners and decision makers in groundwater-investment planning to achieve sustainability.
Highlights
Increasing demands for water due to population growth and industrialization combined with anticipated changes in aquatic resources due to global warming and regional climate change highlight the urgent need for a quantitative methodology that can model groundwater production [1,2,3,4,5,6,7].Groundwater-potential mapping (GPM) is the first and most important step in groundwater management [8]
This study evaluated the performance of the Vise Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR)-random forest (RF)-frequency ratio (FR) ensemble approach for groundwater potential mapping
Three aspects of this study suggest that overfitting could have occurred: the area from which the non-well locations were selected was confined to the region that contained wells even though the study region extended well beyond the region covered by wells, the ratio of 70:30 training to validation datasets was used without an assessment of the accuracy of the sampling ratio, and despite the multicollinearity assessment, groundwater conditioning factors (GWCFs) still had noise
Summary
Groundwater-potential mapping (GPM) is the first and most important step in groundwater management [8]. Since the methods to identify the parameters that influence the spatial distribution of groundwater and the ways to acquire data are evolving, new approaches to develop accurate and useful information for decision makers are needed [9]. GPM is effectively achieved by combining field study, remote sensing (RS), and geographic information system (GIS) methods [10,11]. The growing use of satellite data, thematic maps, and land cover and land use (LULC) data has made it easier to study groundwater potential. The combination of GIS with new modeling methods can be a powerful tool for decision makers [12,13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
