The increasing prevalence of nanoplastics in the environment underscores the need for effective detection and monitoring techniques. Current methods mainly focus on microplastics, while accurate identification of nanoplastics is challenging due to their small size and complex composition. In this work, we combined highly reflective substrates and machine learning to accurately identify nanoplastics using Raman spectroscopy. Our approach established Raman spectroscopy data sets of nanoplastics, incorporated peak extraction and retention data processing, and constructed a random forest model that achieved an average accuracy of 98.8% in identifying nanoplastics. We validated our method with tap water spiked samples, achieving over 97% identification accuracy, and demonstrated the applicability of our algorithm to real-world environmental samples through experiments on rainwater, detecting nanoscale polystyrene (PS) and polyvinyl chloride (PVC). Despite the challenges of processing low-quality nanoplastic Raman spectra and complex environmental samples, our study demonstrated the potential of using random forests to identify and distinguish nanoplastics from other environmental particles. Our results suggest that the combination of Raman spectroscopy and machine learning holds promise for developing effective nanoplastic particle detection and monitoring strategies.
Keywords: Machine Learning; Microplastics; Nanoplastics; Raman Spectroscopy; Random Forest.