Approximately 10% of community water systems in the United States experience a health-based violation of drinking water quality; however, recently allocated funds for improving United States water infrastructure ($50 billion) provide an opportunity to address these issues. The objective of this study was to examine environmental, operational, and sociodemographic drivers of spatiotemporal variability in drinking water quality violations using geospatial analysis and data analytics. Random forest modeling was used to evaluate drivers of these violations, including environmental (e.g., landcover, climate, geology), operational (e.g., water source, system size), and sociodemographic (social vulnerability, rurality) drivers. Results of random forest modeling show that drivers of violations vary by violation type. For example, arsenic and radionuclide violations are found mostly in the Southwest and Southcentral United States related to semiarid climate, whereas disinfection byproduct rule violations are found primarily in Southcentral United States related to system operations. Health-based violations are found primarily in small systems in rural and suburban settings. Understanding the drivers of water quality violations can help develop optimal approaches for addressing these issues to increase compliance in community water systems, particularly small systems in rural areas across the United States.
Keywords: Safe Drinking Water Act; drinking water; random forest modeling; regulatory compliance; violations; water quality.