Learning to Pre-process Laser Induced Breakdown Spectroscopy Signals Without Clean Data

This work tests whether deep neural networks can clean laser induced breakdown spectroscopy (LIBS) signals by using only uncleaned raw measurements. Our view of this problem considers a disentanglement of the effects of the target of interest from those of the nuisance factors (with non-zero mean) by leveraging the vast amounts of redundancies in LIBS data and our proposed learning formulation. This later aims at promoting consistency between repeated measurement views of a target while simultaneously removing consistencies with all other LIBS measurements taken throughout the history of the instrument. Evaluations on real data from the ChemCam instrument onboard the Martian Curiosity rover show a superior performance in cleaning LIBS signals compared to the standard approaches being used by the ChemCam team.