Feasibility of using deep learning techniques such as U-Nets for Raman spectral denoising is investigated alongside classical methods such as improved asymetric least squares. Raman spectral processing pipelines featuring Principal Component Analysis (PCA) and Singular Value Decomposition (SVD) are also being developed, Cluster analysis methods using Gaussian Mixture models is currently studied for PCA results of Raman spectra obtained for ongoing research problems.
