Abstract
The performance of four tree-based classification techniques—classification and regression trees (CART), multi-adaptive regression splines (MARS), random forests (RF) and gradient boosting trees (GBT) were compared against the commonly used logistic regression (LR) analysis to assess aquifer vulnerability in the Ogallala Aquifer of Texas. The results indicate that the tree-based models performed better than the logistic regression model, as they were able to locally refine nitrate exceedance probabilities. RF exhibited the best generalizable capabilities. The CART model did better in predicting non-exceedances. Nitrate exceedances were sensitive to well depths—an indicator of aquifer redox conditions, which, in turn, was controlled by alkalinity increases brought forth by the dissolution of calcium carbonate. The clay content of soils and soil organic matter, which serve as indicators of agriculture activities, were also noted to have significant influences on nitrate exceedances. Likely nitrogen releases from confined animal feedlot operations in the northeast portions of the study area also appeared to be locally important. Integrated soil, hydrogeological and geochemical datasets, in conjunction with tree-based methods, help elucidate processes controlling nitrate exceedances. Overall, tree-based models offer flexible, transparent approaches for mapping nitrate exceedances, identifying underlying mechanisms and prioritizing monitoring activities.
Highlights
Nitrate (NO3 -N) is a widespread environmental contaminant that is commonly detected in groundwater supplies and can cause severe health effects, both in children and adults [1]
Nitrates in groundwater can arise from multiple sources, including, but not limited to, the use of fertilizers, improper waste management practices from animal feed operations, inadequate treatment of household wastewater prior to its discharge in the environment, as well as from natural sources
Logistic regression is a popular technique for mapping aquifer vulnerability; it is used here to benchmark the performance of tree-based modeling schemes
Summary
Nitrate (NO3 -N) is a widespread environmental contaminant that is commonly detected in groundwater supplies and can cause severe health effects, both in children and adults [1]. Many groundwater dependent public water supply systems in the US and in the rural parts of Texas have seen increases in the violation of nitrate drinking water quality standards over the last few decades [2]. Over 13 million households in the United States (approximately 15% of the nation’s population) rely on unregulated private water wells to meet their drinking water needs [3]. A large majority of this population is rural and susceptible to exposure to elevated nitrate concentrations through their drinking water sources [4]. Reliance on private water wells is even higher in under-developed and developing nations and, as such, efforts to characterize nitrate in groundwater aquifers are actively being pursued by several local, state and national agencies
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
