TY - JOUR
T1 - Unveiling PFAS hazard in European surface waters using an interpretable machine-learning model
AU - Zhao, Li
AU - Chen, Jian
AU - Wen, Jiaqi
AU - Li, Yangjie
AU - Zhang, Yingjie
AU - Wu, Qunyue
AU - Yu, Gang
N1 - This work was supported by the Key Project for the Construction of the Drug Regulatory Science System by the National Medical Products Administration (RS2024C003), the Guangdong Provincial Science and Technology Program (2023A1111120025), and the 2025 Science and Technology Innovation Project of Guangdong Provincial Medical Products Administration (S2024YDZ020).
Publisher Copyright:
© 2025 The Authors. Published by Elsevier Ltd.
PY - 2025/4/30
Y1 - 2025/4/30
N2 - Per- and polyfluoroalkyl substances (PFAS), commonly known as “forever chemicals”, are ubiquitous in surface waters and potentially threaten human health and ecosystems. Despite extensive monitoring efforts, PFAS risk in European surface waters remain poorly understood, as performing PFAS analyses in all surface waters is remarkably challenging. This study developed two machine-learning models to generate the first maps depicting the concentration levels and ecological risks of PFAS in continuous surface waters across 44 European countries, at a 2-km spatial resolution. We estimated that nearly eight thousand individuals were affected by surface waters with PFAS concentrations exceeding the European Drinking Water guideline of 100 ng/L. The prediction maps identified surface waters with high ecological risk and PFAS concentration (>100 ng/L), primarily in Germany, the Netherlands, Portugal, Spain, and Finland. Furthermore, we quantified the distance to the nearest PFAS point sources as the most critical factor (14 %–19 %) influencing the concentrations and ecological risks of PFAS. Importantly, we determined a threshold distance (4.1–4.9 km) from PFAS point sources, below which PFAS hazards in surface waters could be elevated. Our findings advance the understanding of spatial PFAS pollution in European surface waters and provide a guideline threshold to inform targeted regulatory measures aimed at mitigating PFAS hazards.
AB - Per- and polyfluoroalkyl substances (PFAS), commonly known as “forever chemicals”, are ubiquitous in surface waters and potentially threaten human health and ecosystems. Despite extensive monitoring efforts, PFAS risk in European surface waters remain poorly understood, as performing PFAS analyses in all surface waters is remarkably challenging. This study developed two machine-learning models to generate the first maps depicting the concentration levels and ecological risks of PFAS in continuous surface waters across 44 European countries, at a 2-km spatial resolution. We estimated that nearly eight thousand individuals were affected by surface waters with PFAS concentrations exceeding the European Drinking Water guideline of 100 ng/L. The prediction maps identified surface waters with high ecological risk and PFAS concentration (>100 ng/L), primarily in Germany, the Netherlands, Portugal, Spain, and Finland. Furthermore, we quantified the distance to the nearest PFAS point sources as the most critical factor (14 %–19 %) influencing the concentrations and ecological risks of PFAS. Importantly, we determined a threshold distance (4.1–4.9 km) from PFAS point sources, below which PFAS hazards in surface waters could be elevated. Our findings advance the understanding of spatial PFAS pollution in European surface waters and provide a guideline threshold to inform targeted regulatory measures aimed at mitigating PFAS hazards.
KW - Affected population
KW - Ecosystem safety
KW - Interpretable machine learning
KW - PFAS contamination
KW - Tipping point
UR - https://www.sciencedirect.com/science/article/pii/S0160412025002557?via%3Dihub
U2 - 10.1016/j.envint.2025.109504
DO - 10.1016/j.envint.2025.109504
M3 - Journal article
SN - 0160-4120
VL - 199
JO - Environment International
JF - Environment International
M1 - 109504
ER -
