Using Geospatial Data and Random Forest To Predict PFAS Contamination in Fish Tissue in the Columbia River Basin, United States

Abstract

Decision makers in the Columbia River Basin (CRB) are currently challenged with identifying and characterizing the extent of per- and polyfluoroalkyl substances (PFAS) contamination and human exposure to PFAS. This work aims to develop and pilot a methodology to help decision makers target and prioritize sampling investigations and identify contaminated natural resources. Here we use random forest models to predict ∑PFAS in fish tissue; understanding PFAS levels in fish is particularly important in the CRB because fish can be a major component of tribal and indigenous people diet. Geospatial data, including land cover and distances to known or potential PFAS sources and industries, were leveraged as predictors for modeling. Models were developed and evaluated for Washington state and Oregon using limited available empirical data. Mapped predictions show several areas where detectable concentrations of PFAS in fish tissue are predicted to occur, but prior sampling has not yet confirmed. Variable importance is analyzed to identify potentially important sources of PFAS in fish in this region. The cost-effective methodologies demonstrated here can help address sparsity of existing PFAS occurrence data in environmental media in this and other regions while also giving insights into potentially important drivers and sources of PFAS in fish.

Application Of Machine Learning To Understand Pfas Occurrence, Distribution, Transport And Removal In Water

“…Split such as 80:20 was used by several authors (Azhagiya Singam et al, 2020;Dong et al, 2023;Hosseinzadeh et al, 2022;McMahon et al, 2022). Hu et al, (2021) divided the domestic well PFAS data in the ratio 80:20; this is consistent with the ratio adopted by DeLuca et al, (2023) who used a 100-iteration Monte Carlo holdout scheme to split PFAS data from Columbia River Basin fish tissue. Other split ratios used by authors include 70:30 Ng, 2019) and75:25 (Fernandez et al, 2023).…”

“…Kwon et al, (2023) predicted bioactivities of PFAS. Other data sources include the United states environmental protection agency's water quality portal (USEPA) (Azhagiya Singam et al, 2020;DeLuca et al, 2023;Dong et al, 2023), PubChem Bioassay Database (Kwon et al, 2023), Pennsylvania Water quality network (Breitmeyer et al, 2023), from previously published studies on PFAS (Karbassiyazdi et al, 2022;Kibbey et al, 2020;Patel et al, 2022), lake and river data (Antell et al, 2023;Stults et al, 2023), Minnesota department of health (MDH) Government agency data (Breitmeyer et al, 2023;Fernandez et al, 2023;Li and Gibson, 2023) and experimental data (Cao et al, 2022;Sörengård et al, 2022;Wang et al, 2022). Some authors combined several public data for their machine learning predictions.…”

“…It is utilized when there is a risk of big errors. This metric was applied to the RF model which was used to predict PFAS contamination in fish tissue (DeLuca et al, 2023). Several authors used this metric for the performance evaluation of several models (Cao et al, 2022;Feinstein et al, 2021;Hu et al, 2023).…”

“…The best-performing classification model was the 5 ng/g and 1.5ng/g threshold PFAS concentration had the best and worst performance based on their mean AUC, accuracy, sensitivity, and specificity over 100 Monte Carlo iterations (DeLuca et al, 2023).…”

PFAS in Nigeria: Identifying data gaps that hinder assessments of ecotoxicological and human health impacts

“…Furthermore, PFAS are employed in the formulation of various types of paints. The unique properties of PFAS, such as their resistance to heat, chemicals, and oil, as well as their ability to provide a smooth, durable finish, make them valuable additives in paint products [ 40 ]. Per- and polyfluoroalkyl substances contribute significantly to the durability and robustness required to withstand extreme conditions in aircraft paints.…”