Machine learning-fugacity framework reveals the fate and environmental drivers of per- and polyfluoroalkyl substances in a mountainous river.

Machine learning and fugacity modeling reveal that river sediments intercept 26.6% of PFAS flux and altitude correlates with higher short-chain PFAS levels in the Third Pole-Tibetan Plateau.

• Why it matters: Understanding the environmental fate of PFAS in fragile, high-altitude ecosystems is crucial due to limited data and the potential impact of climate change-driven glacier meltwater on contaminant distribution.
• What they did: The study combined field measurements of PFAS across water, sediments, and soils with machine learning models using meteorological and geographic data, and established a fugacity model to simulate PFAS migration pathways.
• The result: Findings suggest that river sediments act as major sinks for PFAS, with altitude influencing contaminant patterns, and climate change may increase PFAS accumulation via glacier meltwater, providing a transferable framework for similar ecosystems.