Deep Spectral CNN for Laser Induced Breakdown Spectroscopy
This work addresses the problem of robust chemical analysis from LIBS signals for remote sensing applications, particularly relevant for space exploration missions.
This paper introduces a spectral convolutional neural network (CNN) designed to process laser induced breakdown spectroscopy (LIBS) signals. The CNN effectively disentangles spectral signals from sensor uncertainty and provides qualitative and quantitative chemical content measurements, outperforming existing Mars Science Lab methods for pre-processing and calibration on Mars rover 'Curiosity' data.
This work proposes a spectral convolutional neural network (CNN) operating on laser induced breakdown spectroscopy (LIBS) signals to learn to (1) disentangle spectral signals from the sources of sensor uncertainty (i.e., pre-process) and (2) get qualitative and quantitative measures of chemical content of a sample given a spectral signal (i.e., calibrate). Once the spectral CNN is trained, it can accomplish either task through a single feed-forward pass, with real-time benefits and without any additional side information requirements including dark current, system response, temperature and detector-to-target range. Our experiments demonstrate that the proposed method outperforms the existing approaches used by the Mars Science Lab for pre-processing and calibration for remote sensing observations from the Mars rover, 'Curiosity'.