T65 Arsenic, Fluoride, and Other Geogenic Contaminants in Groundwater: Advances in Application of Data Science, Machine Learning for Risk Assessment and Monitoring for Sustainable Mitigation of Associated Health Hazards

Sunday, 15 October 2023
1:30 PM - 5:30 PM
319

PROBABILISTIC MAPPING OF HIGH-HAZARD ZONES OF DISSOLVED MANGANESE AND IRON IN GROUNDWATER OF THE SHENANDOAH VALLEY, VIRGINIA

Paper number: T65-4
Program: Technical Sessions
Time: 2:05 PM – 2:25 PM

Authors

Abstract

The Shenandoah Valley is located within the Valley and Ridge province of the Appalachians, stretching along an elongated strip of ~300 km. Of its population, >36% relies on groundwater from private wells as their drinking water source. Water-quality testing by the Virginia Household Water Quality Program (VAHWQP) and the United States Geological Survey (USGS) National Water Information System (NWIS) reveals elevated levels of dissolved solutes, like manganese (Mn) and iron (Fe) in the Valley’s groundwater. Despite being essential nutrients, prolonged exposure to elevated Mn levels in drinking water may cause significant health risks, including neurological impairments, conotruncal heart diseases, and increased cancer mortality, while the combination of Mn and Fe have been associated with low birth weights in babies, among other effects. Deploying the Random Forest (RF) classification algorithm, this study utilizes the VAHWQP and USGS NWIS datasets to predictively model the spatial occurrence of high-hazard zones for groundwater Mn (>0.08 mg/L, World Health Organization's health-based guideline for Mn in drinking water) and Fe (>0.1 mg/L, based on previous research suggesting the given groundwater Fe threshold as an indicator of simultaneous mobilization of geogenic contaminants) across the Valley. The models reveal widespread occurrence of Fe-hazard in the northern parts of the Valley, while the highest probabilities of Mn hazard align with the NE-SW Valley axis to the north and central parts. Besides, sporadic occurrences of these high-hazard zones are observed throughout the area. The area under the curve (AUC) values are 93.5% for the Mn model and 92.2% for the Fe model on the test data, suggesting good model predictive ability. Such contaminant mapping efforts are helpful in delineating the potentially unsafe aquifer zones and highlight the necessity for water testing prior to utilizing the wells in the high hazard zones as a source of drinking water.

Geological Society of America Abstracts with Programs. Vol. 55, No. 6

doi: 10.1130/abs/2023AM-392920

© Copyright 2023 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.