We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Research Progress on the Application of Machine Learning in New Pollutants Studies
Summary
This review examines how machine learning is being applied to study new pollutants including microplastics, pharmaceuticals, and PFAS, covering detection, migration modeling, risk assessment, and remediation design. The authors identify that deep learning and ensemble methods have shown the strongest performance across these applications.
New Pollutants (NP) are widely distributed and frequently detected in oceans, soil, the atmosphere, and drinking water. With their persistent accumulation and diffusion in the environment, the potential ecological and health risks of NP have become increasingly prominent, drawing significant attention from both academia and the public. Currently, researchers worldwide have conducted extensive systematic studies on the identification and detection of NP, their migration and transformation patterns, ecotoxicological effects, and efficient removal technologies.Machine Learning, as an advanced data modeling and analysis method, can significantly enhance the timeliness and predictive accuracy of NP research through big data-driven forecasting. This review summarizes the current applications of ML in the identification, distribution, and toxicological effects of persistent organic pollutants, endocrine disrupting chemicals, antibiotics and microplastics. Additionally, it provides insights into future research directions, such as exploring interpretable ML models, establishing data-sharing platforms, enabling real-time pollutant monitoring and establishing an association model between traditional and new pollutants.