Revealing the sources of arsenic in private well water using Random Forest Classification and Regression.

Exposure to arsenic through private drinking water wells causes serious human health risks throughout the globe. Water testing data indicates there is arsenic contamination in private drinking water wells across New Jersey. To reduce the adverse health risk due to exposure to arsenic in drinking water, it is necessary to identify arsenic sources affecting private wells. Private wells are not regulated by any federal or state agencies through the Safe Drinking Water Act and therefore information is often lacking. To this end, we have developed machine learning algorithms including Random Forest Classification and Regression to decipher the factors contributing to higher arsenic concentration in private drinking water wells in west-central New Jersey. Arsenic concentration in private drinking water wells served as a response variable while explanatory variables were geological bedrock type, soil type, drainage class, land use/cover, and presence of orchards, contaminated sites, and abandoned mines within the 152.4-meter (500 ft) radius of each well. Random Forest Classification and Regression achieved 66 % and 55 % prediction accuracies for arsenic concentration in private drinking water wells, respectively. Overall, both models identify that bedrock, soil, land use/cover, and drainage type (in descending order) are the most important variables contributing to higher arsenic concentration in well water. These models further identify bedrock subgroups at a finer scale including Passaic Formation, Lockatong Formation, Stockton Formation contributing significantly to arsenic concentration in well water. Identification of sources of arsenic contamination in private drinking water wells at such a fine scale facilitates development of more targeted outreach as well as mitigation strategies to improve water quality and safeguard human health.

Application of an environmental decision support system to a water quality trading program affected by surface water diversions.

Environmental decision support systems (EDSSs) are an emerging tool used to integrate the evaluation of highly complex and interrelated physicochemical, biological, hydrological, social, and economic aspects of environmental problems. An EDSS approach is developed to address hot-spot concerns for a water quality trading program intended to implement the total maximum daily load (TMDL) for phosphorus in the Non-Tidal Passaic River Basin of New Jersey. Twenty-two wastewater treatment plants (WWTPs) spread throughout the watershed are considered the major sources of phosphorus loading to the river system. Periodic surface water diversions to a major reservoir from the confluence of two key tributaries alter the natural hydrology of the watershed and must be considered in the development of a trading framework that ensures protection of water quality. An EDSS is applied that enables the selection of a water quality trading framework that protects the watershed from phosphorus-induced hot spots. The EDSS employs Simon's (1960) three stages of the decision-making process: intelligence, design, and choice. The identification of two potential hot spots and three diversion scenarios enables the delineation of three management areas for buying and selling of phosphorus credits among WWTPs. The result shows that the most conservative option entails consideration of two possible diversion scenarios, and trading between management areas is restricted accordingly. The method described here is believed to be the first application of an EDSS to a water quality trading program that explicitly accounts for surface water diversions.