235-7 Geospatial machine learning for predicting groundwater arsenic contamination: Implications for human health

Session: Advancing the Understanding and Management of Groundwater Pollution with Arsenic and Other Geogenic Contaminants Using Geospatial Tools, Machine Learning, and Data Science, Part I

Presenting Author:

Authors:

Abstract:

Arsenic (As) contamination of groundwater in parts of South and Southeast Asia is a public health disaster. Millions of people living in these regions may be chronically exposed to drinking water with As concentrations above the World Health Organization’s provisional guideline of 10 μg/L. Recent field investigations have shown that the distribution of groundwater As in some shallow aquifers is changing rapidly, probably because of irrigation pumping. This study compares a decade-old dataset of As concentration measurements in groundwater with a dataset of recent measurements using geospatial machine learning techniques. We observed that the probability of As concentrations >10 μg/L was significantly higher in regions between major rivers than in areas closer to river channels, where higher proportions of As concentrations >10 μg/L had been observed in earlier years. The greater likelihood that elevated concentrations of As are present away from the river channel could be attributed to the transport and flushing of aquifer As due to irrigation pumping. We estimated that several million people could be chronically exposed to As concentrations >10 μg/L. This high population-level exposure to elevated As concentrations could be reduced through targeted well-testing campaigns, promoting well-switching, provisions for safe water access, and developing plans for raising public awareness. Policymakers may use the maps presented here to target high-risk localities for the priority implementation of piped water supply to help reduce human suffering.

Geological Society of America Abstracts with Program. Vol. 57, No. 6, 2025

doi: 10.1130/abs/2025AM-9034

© Copyright 2025 The Geological Society of America (GSA), all rights reserved.