Analysis of laser ablation spectral data using dimensionality reduction techniques: PCA, t-SNE and UMAP

Laser ablation is among the various methods employed for expediting the prototyping of printed circuit boards. Laser-induced breakdown spectroscopy (LIBS) serves as a convenient technique for overseeing the targeted elimination of thin layers with lasers. Consequently, this approach facilitates the rapid prototyping of printed circuit boards. In this paper the obtained LIBS data are analyzed by using data dimension reduction techniques: principal component analysis (PCA), t-SNE and UMAP to obtain an indication that copper layer is fully removed. For machine learning approach to data analysis we use Solo+Mia software package (Version 9.1, Eigenvector Research Inc, USA).