Abstract
Microplastic analysis is a crucial step for locating the environmental contamination sources and controlling plastic contamination. A popular tool like Fourier transform infrared (FTIR) spectroscopy is capable of identifying plastic types and can be carried out through a variety of containers. Unfortunately, sample collection from water sources like rivers usually involves filtration so the measurements inevitably include the membrane filter that also has its own FTIR characteristic bands. Furthermore, when plastic particles are small, the membrane filter's spectrum may overwhelm the desired plastics' spectrum. In this study, we proposed a novel preprocessing method based on the dictionary learning technique for decomposing the variations within the acquired FTIR spectra and capturing the membrane filter's characteristic bands for the effective removal of these unwanted signals. We break down the plastic analysis task into two subtasks - membrane filter removal and plastic classification - to increase the explainability of the method. In the experiments, our method demonstrates a 1.5-fold improvement compared with baseline, and yields comparable results compared to other state-of-the-art methods such as UNet when applied to noisy spectra with low signal-to-noise ratio (SNR), but offers explainability, a crucial quality that is missing in other state-of-the-art methods. The limitations of the method are studied by testing against generated spectra with different levels of noise, with SNR ranging from 0 to - 30dB, as well as samples collected from the lab. The components/atoms learned from the dictionary learning technique are also scrutinized to describe the explainability and demonstrate the effectiveness of our proposed method in practical applications.