Customizable Machine-Learning Models for Rapid Microplastic Identification Using Raman Microscopy

Abstract

Raman spectroscopy is commonly used in microplastics identification, but equipment variations yield inconsistent data structures that disrupt the development of communal analytical tools. We report a strategy to overcome the issue using a database of high-resolution, full-window Raman spectra. This approach enables customizable analytical tools to be easily created─a feature we demonstrate by creating machine-learning classification models using open-source random-forest, K-nearest neighbors, and multi-layer perceptron algorithms. These models yield >95% classification accuracy when trained on spectroscopic data with spectroscopic data downgraded to 1, 2, 4, or 8 cm–1 spacings in Raman shift. The accuracy can be maintained even in non-ideal conditions, such as with spectroscopic sampling rates of 1 kHz and when microplastic particles are outside the focal plane of the laser. This approach enables the creation of classification models that are robust and adaptable to varied spectrometer setups and experimental needs.