Random forest microplastic classification using spectral subsamples of FT-IR hyperspectral images

In this work, a random decision forest model is built for fast identification of Fourier-transform infrared spectra of the eleven most common types of microplastics in the environment. The random decision forest input data is reduced to a combination of highly discriminative single wavenumbers selected using a machine learning classifier. This dimension reduction allows input from systems with individual wavenumber measurements, and decreases prediction time. The training and testing spectra are extracted from Fourier-transform infrared hyperspectral images of pure-type microplastic samples, automatizing the process with reference spectra and a fast background correction and identification algorithm. Random decision forest classification results are validated using procedurally generated ground truth. The classification accuracy achieved on said ground truths are not expected to carry over to environmental samples as those usually contain a broader variety of materials.