Abstract
The goals of environmental legislation and associated regulations are to protect public health, natural resources, and ecosystems. In this context, monitoring programs should provide timely and relevant information so that the regulatory community can implement legislation in a cost-effective and efficient manner. The Safe Drinking Water Act (SDWA) of 1974 attempts to ensure that public water systems (PWSs) supply safe water to its consumers. As is the case with many other federal environmental statutes, SDWA monitoring has been implemented in relatively uniform fashion across the United States. In this three part series, spatial and temporal patterns in water quality data are utilized to develop, compare, and evaluate the economic performance of alternative place-based monitoring approaches to current monitoring practice. Part II: Several factors affect the performance of monitoring strategies, including: measurable objectives, required precision in estimates, acceptable confidence levels of such estimates, available budget for sampling. In this paper, we develop place-based monitoring strategies based on extensive analysis of available historical water quality data (1960-1994) of 19 Iowa community water systems. These systems supply potable water to over 350,000 people. In the context of drinking water, the objective is to protect public health by utilizing monitoring resources to characterize contaminants that are detectable, and are close to exceeding health standards. A place-based monitoring strategy was developed in which contaminants were selected based on their historical occurrence, rather than their appearance on the SDWA contaminant list. In a subset of the water systems, the temporal frequency of monitoring for one ubiquitous contaminant, nitrate, was tailored to patterns in its historical occurrence and concentration. Three sampling allocation models (linear, quadratic, and cubic) based on historic patterns in peak occurrence were developed and evaluated. Random and fixed-interval sampling strategies within the context of such models were also developed and evaluated. Strategies were configured to incorporate a variety of options for frequency and number of samples (depending on budget and the desired precision in estimate of peak concentrations).
Original language | English (US) |
---|---|
Pages (from-to) | 91-102 |
Number of pages | 12 |
Journal | Environmental Monitoring and Assessment |
Volume | 143 |
Issue number | 1-3 |
DOIs | |
State | Published - Aug 2008 |
Externally published | Yes |
Bibliographical note
Funding Information:Acknowledgments The research reported in this paper was supported in part by the USDA (CSREES) grant no. 2001-51130-11373 “Water Quality Protection in Agroecosystems: Integrating Science, Technology, and Policy at the Watershed Scale” to the University of Iowa (2001–2005). The Geography Department, the UI Honors Program and the College of Liberal Arts and Sciences provided significant in-kind resources in the form of space, computational support, and several student research internships. Data was provided by the Center for Health Effects of Environmental Contamination (CHEEC) of the University of Iowa and the Iowa Geological Survey Bureau of the Iowa Department of Natural Resources. Additional thanks are due Dr. Michael Wichman and Sherri Marine of the University Hygienic Laboratory for their assistance with 4The available methods for coping with “censored data” or non-detections range from using simple substitution (e.g. assigning the detection limit, zero, or 1/2 detection limit), to using distributions (e.g. lognormal) to estimate the censored values, to using “robust” methods which combine extrapolation with the shape of the distribution above the detection limit to estimate censored values (Helsel and Hirsch 2002; Keith et al. 1983; Porter et al. 1988). This analysis was performed in the context of the SDWA and public health, and no research has shown a link to potential health consequences of nitrate exposure below the detection limit. Furthermore, choosing 1/2 the detection limit versus assigning the detection limit or zero, or any other method would have no impact on any of the percentiles examined in this research (i.e. especially the 99th percentile) unless a significant portion of the dataset were censored. Therefore, the choice of how to cope with below detection limit values is ultimately inconsequential in this context.
Copyright:
Copyright 2008 Elsevier B.V., All rights reserved.
Keywords
- Community water systems
- Iowa
- Monitoring strategy development
- Performance measures
- Place-based monitoring
- Safe drinking water act
- Screening
- Spatial variability
- Temporal variability
- USA
- Water quality