Machine learning assisted dual-functional nanophotonic sensor for organic pollutant detection and degradation in water

This study introduces a dual-functional thin film (AgNP-ZnONR-SNF) for water purification and organic pollutant sensing. The 3D fibrous structure enables efficient (98%+) piezo- and photo-catalytic degradation of pollutants under UV irradiation. Ag nanoparticles enhance Surface-Enhanced Raman Spectroscopy (SERS) signals, achieving a 1056 enhancement factor and a 1 pg mL⁻¹ detection limit. A machine learning algorithm allows accurate (92.3% accuracy, 89.3% specificity) qualitative and quantitative detection of multiple contaminants directly from Raman spectra without preprocessing.

Junhu Zhou, Ziqian Wu, Congran Jin, John X. J. Zhang