Validity of spatial models of arsenic concentrations in private well water

Abstract

Objective-Arsenic is a pervasive contaminant in underground aquifers worldwide, yet documentation of health effects associated with low-to-moderate concentrations (<100 μg/L) has been stymied by uncertainties in assessing long-term exposure. A critical component of assessing exposure to arsenic in drinking water is the development of models for predicting arsenic concentrations in private well water in the past; however, these models are seldom validated. The objective of this paper is to validate alternative spatial models of arsenic concentrations in private well water in southeastern Michigan. Methods-From 1993−2002 the Michigan Department of EnvironmentalQuality analyzed arsenic concentrations in water from 6,050 private wells. This dataset was used to develop several spatial models of arsenic concentrations in well water: proxy wells based on nearest neighbor relationships, averages across geographic regions, and geostatistically-derived estimates based on spatial correlation and geologic factors. Output from these models was validated using arsenic concentrations measured in 371 private wells from 2003−2006.Results-The geostatisical model and nearest neighbor approach outperformed the models based on geographic averages. The geostatistical model produced the highest degree of correlation using continuous data (Pearson's r=0.61; Spearman's rank ρ=0.46) while the nearest neighbor approach produced the strongest correlation (κ weighted =0.58) using an a priori categorization of arsenic concentrations (<5, 5−9.99, 10−19.99, ≥20 μg/L). When the maximum contaminant level was used as a cut-off in a two-category classification (<10, ≥10 μg/L), the nearest neighbor approach and geostatistical model had similar values for sensitivity (0.62−0.63), specificity (0.80), negative predictive value (0.85), positive predictive value (0.53), and percent agreement (75%).Discussion-This validation study reveals that geostatistical modeling and nearest neighbor approaches are effective spatial models for predicting arsenic concentrations in private well water. Further validation analyses in other regions are necessary to indicate how widely these findings may be generalized.

Spatial Modeling for Groundwater Arsenic Levels in North Carolina

“…Recent studies suggest that arsenic concentrations in groundwater may be spatially positively correlated. 19,21,44 We developed spatial statistical models that borrow information from nearby wells to estimate arsenic levels in nondetect and nonsampled wells. Spatial modeling also helps identify spatial patterns in the determinants, which affect not only arsenic levels in a well but also levels in neighboring wells.…”

Lifetime exposure to arsenic in drinking water and bladder cancer: a population-based case–control study in Michigan, USA

“…The geostatistical model predicts arsenic concentration for 500 × 500 m 2 pixels. This model was validated using a separate test dataset of 371 well water measurements, and showed a Pearson’s correlation r = 0.61; predicting above or below a 10 µg/L threshold resulted in sensitivity = 0.62, specificity = 0.80, and 75% agreement [31]. …”

Understanding and forecasting hypoxia using machine learning algorithms

“…Before machine learning algorithms can be executed in the manner that will best explain the phenomena in question, data must first be appropriately prepared (Pyle 1999). Machine learning algorithms such as k-nearest neighbor have been proposed to solve environmental problems from soil water retention (Nemes et al 2008), to arsenic in well-water (Meliker et al 2008), to forest mapping (McRoberts et al 2007). Other popular techniques employed in data-driven modeling efforts are illustrated in the context of river basin management (Solomatine & Ostfeld 2008).…”