Comparison of gradient boosted decision trees and random forest for groundwater potential mapping in Dholpur (Rajasthan)
- PDF / 2,491,324 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 108 Downloads / 213 Views
ORIGINAL PAPER
Comparison of gradient boosted decision trees and random forest for groundwater potential mapping in Dholpur (Rajasthan), India Shruti Sachdeva1
•
Bijendra Kumar1
Accepted: 30 September 2020 Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract In the drought prone district of Dholpur in Rajasthan, India, groundwater is a lifeline for its inhabitants. With population explosion and rapid urbanization, the groundwater is being critically over-exploited. Hence the current groundwater potential mapping study was undertaken to ascertain the areas that are more likely to yield a larger volume of groundwater against those areas that have poor groundwater potential and accordingly perpetuate the much needed damage control. Thematic layers for 14 groundwater influencing factors were considered for the study region, including elevation, slope, aspect, plan curvature, profile curvature, topographic wetness index (TWI), geology, soil, land use, normalized difference vegetation index (NDVI), surface temperature, precipitation, distance from roads, and distance from rivers. These were then subjected to an overlay operation, with the groundwater inventory which comprised of the locations of observational groundwater wells. The resulting geospatial database was then used to train two decision tree based ensemble models: gradient boosted decision trees (GBDT) and random forest (RF). The predictive performance of these models was then compared using various performance metrics such as area under curve (AUC) of receiver operating characteristics (ROC), sensitivity, accuracy, etc. It was found that GBDT (AUC: 0.79) outperformed RF (AUC: 0.71). The validated GBDT model was then used to construct the groundwater potential zonation map. The generated map showed that about 20.2% of the region has very high potential, while 22.6% has high potential to yield groundwater, and approximately 19.9–17.5% of the study region has very low to low groundwater potential. Keywords Groundwater potential mapping Machine learning Ensemble models Random forest Gradient boosted decision trees
1 Introduction Groundwater is one amongst the world’s most over-utilized and under-appreciated natural resources. Water in the saturated zone, residing below the surface of the earth in aquifers, is referred to as groundwater (Fitts 2002). Water from surface water bodies (rivers, ponds, streams, canals, etc.) and rainfall, seeps through the earth’s crust via interconnected networks of channels like crevices, fractures, cracks, crushed zones (fault zones or shear zones), & Shruti Sachdeva [email protected] Bijendra Kumar [email protected] 1
Department of Computer Science and Engineering, Netaji Subhas University of Technology, New Delhi, India
and joints and get collected in the underground reservoirs contributing to the water table (Banks et al. 2002). Most aquifers are identified by the general groundwater characteristics such as consistent temperature, extensive availability, economical extraction, and drought r
Data Loading...
