Generation of synthetic FTIR spectra to facilitate chemical identification of microplastics

In a context where learning databases of microplastic FTIR spectra are often incomplete, the objective of our work was to test whether a synthetic data generation method could be relevant to fill the gaps. To this end, synthetic spectra were generated to create new databases. The effectiveness of machine learning from these databases was then tested and compared with previous results. The results showed that the creation of synthetic learning databases could avoid, to a certain extent, the need for learning databases of environmental microplastics FTIR spectra. However, some limitations were encountered, for example, when two different chemical classes had very similar reference spectra or when the intensities of the bands associated with fouling became too intense. The FTIR study of the ageing and fouling of microplastics in the natural environment is one of the identified ways that could further improve this approach.