Skip to content
DraconiticResearch
Search Sources API
178,970 studies31 sourcesUpdated 47 min ago
Peer-reviewedCC BYEnvironmental science & technology

Predicting Bioconcentration Factors and Concentrations of Per- and Polyfluoroalkyl Substances in Plants with Machine Learning.

  • Rui Li1
  • Jiyoon Yi2
  • Hui Li1
  • Wei Zhang1,3
  1. 1Department of Plant, Soil and Microbial Sciences, Michigan State University, East Lansing, Michigan48824, United States.
  2. 2Department of Biosystems and Agricultural Engineering, Michigan State University, East Lansing, Michigan48824, United States.
  3. 3Environmental Science and Policy Program, Michigan State University, East Lansing, Michigan48824, United States.
Read full textPDFDOICite

Abstract

Bioconcentration factors (BCF) and concentrations of per- and polyfluoroalkyl substances (PFAS) in crops were predicted by four machine learning models using a newly compiled data set composed of 11 crops, 11 plant tissue compartments, and 21 PFAS, as well as diverse soil properties and cultivation conditions. The eXtreme Gradient Boosting (XGBoost) achieved the best performance, with a coefficient of determination (R2) of 0.951 for Log BCF and 0.943 for Log C. Feature importance analysis showed that soil pH and PFAS carbon chain length are key predictors of BCF. Soil PFAS concentration is the primary input feature for PFAS concentrations in plants and shorter growth-cycle plants accumulated higher PFAS concentrations. Root and leaf tissues were distinguished as the primary compartments of PFAS accumulation, exhibiting the highest BCF and concentration levels. Interestingly, although PFAS accumulation in plants generally shows a negative correlation with carbon chain length, root accumulation has a relatively weaker correlation with high levels of accumulation for both short-chain and long-chain PFAS. In contrast, above-ground tissues (particularly leaves) preferentially accumulate short-chain PFAS. These findings could provide valuable insights into the development of management and mitigation strategies to minimize PFAS accumulation in food crops and subsequently human exposure through the food chain.

Related

  1. MOF-mediated cascade photoreactions under nanoconfinement for defluorination of per- and polyfluoroalkyl substances
    Jingjing Tang, Xiang Zhang, Jie Li +6
    Nature CommunicationsPeer-reviewedCC BY-NC-ND 4.0Full textEnvironmental chemistryCrossref
  2. Online Soil Column Chromatography Coupled with Mass Spectrometry for Studying Sorption of Per- and Polyfluoroalkyl Substances and Other Organic Contaminants
    Anh T. Ngoc Do, Nobuhide Fujitake, Satoshi Endo
    ChemRxivPreprintCC BY-NC-NDFull textEnvironmental chemistryChemRxiv
  3. Structure-related differences in plasma protein binding of per- and polyfluoroalkyl substances in mice and humans
    Chloé Ml. Argoul, Pierre-Louis Toutain, Sarah Berard +3
    Environmental Toxicology and PharmacologyPeer-reviewedCC BY4 citedEnvironmental chemistryHAL
  4. Per- and polyfluoroalkyl substances (PFAS) and cancer: knowledge mapping and emerging trends based on a bibliometric analysis
    Siyin Liu, Guoqing Zhang, Meijing Wang +1
    Frontiers in OncologyPeer-reviewedCC BY 4.0Full textEnvironmental chemistryCrossrefEurope PMCPMC
  5. Extraction Strategies for Per- and Polyfluoroalkyl Substances (PFAS): A Critical Comparative Framework Integrating Sensitivity, Sustainability, and Analytical Trade-offs
    Muhammad Bilal, Mahnoor Saeed, Ayela Akbar +5
    ChemRxivPreprintCC BYFull textEnvironmental chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@article{li2026predicting,
  title = {{Predicting Bioconcentration Factors and Concentrations of Per- and Polyfluoroalkyl Substances in Plants with Machine Learning.}},
  author = {Rui Li and Jiyoon Yi and Hui Li and Wei Zhang},
  journal = {Environmental science \& technology},
  year = {2026},
  month = sep,
  doi = {10.1021/acs.est.6c10458},
  url = {https://europepmc.org/article/MED/42915432},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Predicting Bioconcentration Factors and Concentrations of Per- and Polyfluoroalkyl Substances in Plants with Machine Learning.
AU  - Rui Li
AU  - Jiyoon Yi
AU  - Hui Li
AU  - Wei Zhang
PY  - 2026
DA  - 2026/09/01
JO  - Environmental science & technology
DO  - 10.1021/acs.est.6c10458
UR  - https://europepmc.org/article/MED/42915432
AB  - Bioconcentration factors (BCF) and concentrations of per- and polyfluoroalkyl substances (PFAS) in crops were predicted by four machine learning models using a newly compiled data set composed of 11 crops, 11 plant tissue compartments, and 21 PFAS, as well as diverse soil properties and cultivation conditions. The eXtreme Gradient Boosting (XGBoost) achieved the best performance, with a coefficient of determination (R2) of 0.951 for Log BCF and 0.943 for Log C. Feature importance analysis showed that soil pH and PFAS carbon chain length are key predictors of BCF. Soil PFAS concentration is the primary input feature for PFAS concentrations in plants and shorter growth-cycle plants accumulated higher PFAS concentrations. Root and leaf tissues were distinguished as the primary compartments of PFAS accumulation, exhibiting the highest BCF and concentration levels. Interestingly, although PFAS accumulation in plants generally shows a negative correlation with carbon chain length, root accumulation has a relatively weaker correlation with high levels of accumulation for both short-chain and long-chain PFAS. In contrast, above-ground tissues (particularly leaves) preferentially accumulate short-chain PFAS. These findings could provide valuable insights into the development of management and mitigation strategies to minimize PFAS accumulation in food crops and subsequently human exposure through the food chain.
SN  - 0013-936X
SN  - 1520-5851
ER  -