Deep Spectral CNN for Laser Induced Breakdown Spectroscopy

TL;DR

This paper introduces a spectral CNN that enhances LIBS signal processing by simultaneously disentangling sensor uncertainties and calibrating chemical content, enabling real-time analysis without extra side information.

Contribution

The novel spectral CNN model improves LIBS data calibration and pre-processing, outperforming existing methods used in Mars rover remote sensing.

Findings

Outperforms existing LIBS pre-processing techniques

Enables real-time spectral analysis without additional side info

Effective in Mars rover remote sensing applications

Abstract

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'.