Answers are grounded in this paper and cite their sources.
Perfluoroalkyl and polyfluoroalkyl substances (PFASs) are emerging persistent organic pollutants. This study developed a multitask learning-based quantitative structure–property relationship (QSPR) model to simultaneously predict the organic carbon–water partition coefficient (log Koc) and bioconcentration factor (log BCF). The model exhibited strong predictive performance and goodness-of-fit. Mechanistic interpretation indicated that log Koc is primarily governed by molecular polarity and nonpolar surface area, while log BCF is influenced by atomic charge and polarity, with carbon-chain length being a key cross-media factor. This work offers a novel approach for forecasting PFASs' environmental behavior and advances machine learning in environmental science.
No takes yet. Share an insight, caveat, or question.
Duan et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: