Unveiling PFAS hazard in European surface waters using an interpretable machine-learning model

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 i...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Zhao, Jian Chen, Jiaqi Wen, Yangjie Li, Yingjie Zhang, Qunyue Wu, Gang Yu
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Environment International
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0160412025002557
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850192910822146048
author Li Zhao
Jian Chen
Jiaqi Wen
Yangjie Li
Yingjie Zhang
Qunyue Wu
Gang Yu
author_facet Li Zhao
Jian Chen
Jiaqi Wen
Yangjie Li
Yingjie Zhang
Qunyue Wu
Gang Yu
author_sort Li Zhao
collection DOAJ
description 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.
format Article
id doaj-art-006596a3a1c64d45b6a8e89fee6018fe
institution OA Journals
issn 0160-4120
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Environment International
spelling doaj-art-006596a3a1c64d45b6a8e89fee6018fe2025-08-20T02:14:24ZengElsevierEnvironment International0160-41202025-05-0119910950410.1016/j.envint.2025.109504Unveiling PFAS hazard in European surface waters using an interpretable machine-learning modelLi Zhao0Jian Chen1Jiaqi Wen2Yangjie Li3Yingjie Zhang4Qunyue Wu5Gang Yu6Guangdong Institute for Drug Control, Guangzhou 510006, China; School of Environment, South China Normal University, Guangzhou 510006, ChinaState Key Laboratory of Environmental and Biological Analysis, Department of Chemistry, Hong Kong Baptist University, 999077, Hong Kong Special Administrative Region; Corresponding authors.Department of Civil and Environmental Engineering, Princeton University, Princeton, NJ 08544, United StatesGuangdong Institute for Drug Control, Guangzhou 510006, China; Corresponding authors.State Key Laboratory of Environmental and Biological Analysis, Department of Chemistry, Hong Kong Baptist University, 999077, Hong Kong Special Administrative RegionGuangdong Institute for Drug Control, Guangzhou 510006, ChinaAdvanced Interdisciplinary Institute of Environment and Ecology, Guangdong Provincial Key Laboratory of Wastewater Information Analysis and Early Warning, Beijing Normal University, Zhuhai 519087, ChinaPer- 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.http://www.sciencedirect.com/science/article/pii/S0160412025002557PFAS contaminationAffected populationEcosystem safetyInterpretable machine learningTipping point
spellingShingle Li Zhao
Jian Chen
Jiaqi Wen
Yangjie Li
Yingjie Zhang
Qunyue Wu
Gang Yu
Unveiling PFAS hazard in European surface waters using an interpretable machine-learning model
Environment International
PFAS contamination
Affected population
Ecosystem safety
Interpretable machine learning
Tipping point
title Unveiling PFAS hazard in European surface waters using an interpretable machine-learning model
title_full Unveiling PFAS hazard in European surface waters using an interpretable machine-learning model
title_fullStr Unveiling PFAS hazard in European surface waters using an interpretable machine-learning model
title_full_unstemmed Unveiling PFAS hazard in European surface waters using an interpretable machine-learning model
title_short Unveiling PFAS hazard in European surface waters using an interpretable machine-learning model
title_sort unveiling pfas hazard in european surface waters using an interpretable machine learning model
topic PFAS contamination
Affected population
Ecosystem safety
Interpretable machine learning
Tipping point
url http://www.sciencedirect.com/science/article/pii/S0160412025002557
work_keys_str_mv AT lizhao unveilingpfashazardineuropeansurfacewatersusinganinterpretablemachinelearningmodel
AT jianchen unveilingpfashazardineuropeansurfacewatersusinganinterpretablemachinelearningmodel
AT jiaqiwen unveilingpfashazardineuropeansurfacewatersusinganinterpretablemachinelearningmodel
AT yangjieli unveilingpfashazardineuropeansurfacewatersusinganinterpretablemachinelearningmodel
AT yingjiezhang unveilingpfashazardineuropeansurfacewatersusinganinterpretablemachinelearningmodel
AT qunyuewu unveilingpfashazardineuropeansurfacewatersusinganinterpretablemachinelearningmodel
AT gangyu unveilingpfashazardineuropeansurfacewatersusinganinterpretablemachinelearningmodel