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

This study presents a dual-functional thin film, known as Ag nanoparticles decorated, ZnO nanorods coated silica nanofibers (AgNP-ZnONR-SNF), which demonstrates remarkable capabilities in both water purification and organic pollutants sensing. The 3D fibrous structure of ZnONR-SNF provides a large surface-area-to-volume ratio for piezo- and photo-catalytic degradation of organic pollutants under UV irradiation, achieving over 98% efficiency. Ag nanoparticles decorated on ZnONR-SNF form "hot-spot" that significantly enhance the surface-enhanced Raman spectroscopy (SERS) signal, resulting in an enhancement factor of 1056 and an experimental detection limit of 1 pg mL⁻¹. Furthermore, a machine learning algorithm is developed for the qualitative and quantitative detection of multiple contaminants, achieving high accuracy (92.3%) and specificity (89.3%) without the need for preliminary processing of Raman spectra. This work provides a promising nanoengineering solution for water purification and sensing with improved detection accuracy, purification efficiency, and cost-effectiveness.

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