Speaker
Description
Microplastic fragments, such as polypropylene (PP), polyethylene (PE), and polystyrene (PS), persist in aquatic environments, where they can act as carriers of chemical contaminants while also raising concerns about their direct biological effects. Microplastics have been detected throughout the food chain and even within human tissues, making their reliable identification at trace levels an urgent analytical challenge. Surface-enhanced Raman spectroscopy (SERS) has been suggested as a promising method for the sensitive detection of microplastics.
Machine learning can be a powerful approach to classify SERS spectra. However, developing reliable models requires large, well-labeled data sets, which are challenging to obtain in SERS. To address this limitation, we use synthetic spectra generated from a set of representative SERS peaks of microplastics and evaluate trained models using SERS spectra reported in the literature. Our approach offers a practical and data-efficient strategy for microplastic identification.
본 연구는 2023년도 정부(교육부)의 재원으로 한국연구재단의 G-램프(LAMP) 사업 지원을 받아 수행된 연구임(No. RS-2023-00301702).
This research was supported by Global - Learning & Academic research institution for Master’s·PhD students, and Postdocs(LAMP) Program of the National Research Foundation of Korea(NRF) grant funded by the Ministry of Education(No. RS-2023-00301702).
