Data and Model Archive for Preliminary Machine Learning Models of Manganese and 1,4-Dioxane in Groundwater on Long Island, New York

Publication Date

2023-03-22

Time Period

2022

DeSimone, L.A., 2023, Data and model archive for preliminary machine learning models of manganese and 1,4-dioxane in groundwater on Long Island, New York: U.S. Geological Survey data release, https://doi.org/10.5066/P90AT9YG.

Type: Related Primary Publication

These data and models were compiled and developed to demonstrate the use of machine learning methods to model and map contaminants in groundwater on Long Island. Groundwater on Long Island is the sole source of drinking water for 2.9 million people and is susceptible to contamination from a variety of sources. Manganese and 1,4-dioxane were chosen as representative of contaminants from natural and anthropogenic sources of concern for drinking water on Long Island. The models are considered preliminary because they were based on only a selected fraction of the available data that potentially could be used for modeling and because they could be improved by modeling enhancements, such as methods to address class imbalance in the concentration data. The models are not intended to provide precise estimates of manganese or 1,4-dioxane at any given location, but, even though based on limited data, can be used to generally identify areas where these contaminants may occur to prioritize future monitoring or guide future modeling and mapping efforts.

• USGS Data Release Products