Python Hyperspectral Analysis Tool (PyHAT) Outlier Identification Example

This figure shows an example of outlier identification using PyHAT. The input data were laser induced breakdown spectroscopy (LIBS) spectra. PyHAT was used to apply a baseline correction and normalization to the total intensity for each spectrum. Dimensionality was then reduced using principal components analysis (PCA). Each point on the PCA scores plot corresponds to a spectrum. The isolation forest algorithm was used to identify potential outliers and these have been marked in red.

This figure is one of a series of figures used to demonstrate some of the capabilities of the PyHAT software.