Replication Data for: Raman Spectra for Plastics Identification (RaSPI) and Raman Maps for Plastics Identification (RaMPI) Research

Plastics pollution is a pervasive global issue and machine learning (ML) is gaining traction as a means to facilitate plastics monitoring. The significant interest in Raman spectroscopy in this field is impacted by high variability in publicly available Raman spectra and classification labels. To address this, we provide a collection of 402 high-resolution Raman spectra (Raman spectra for plastics identification; RaSPI) and 34 two-dimensional Raman spectroscopic maps containing 32,389 additional spectra (Raman maps for plastics identification; RaMPI). The spectra offer samples from diverse sources, including from environmental pollution, variability in (unknown) additives, high signal:noise ratio, and continuous data with <1 cm-1 spacing between 100 and 4000 cm-1 (RaSPI) or 700 and 1800 cm-1 (RaMPI). All spectra have been manually assigned as one of 14 different plastic type classifications. The consistency and quality of these datasets make them high-value resources for researchers active in a range of topics, including training ML models for microplastics research, for developing spectroscopic processing algorithms, or for those seeking datasets to test their methodologies against.