Machine Learning for Planetary in-situ Spectroscopic data

The junior research group Machine Learning for Planetary in-situ Spectroscopic data in the department of In-situ Sensing investigates innovative data analysis strategies using algorithms from the field of machine learning (ML) for the analysis of spectroscopic data. We focus on planetary in-situ measured data with spectroscopic techniques like LIBS (laser-induced breakdown spectroscopy) and Raman spectroscopy. We analyze both data returned from planetary exploration instruments such as the LIBS instrument ChemCam belonging to the payload of NASAs Mars Science Laboratory (MSL) and spectroscopic data acquired in the laboratory or with mobile instrumentation in the field.