Convolutional Neural Network Chemometrics for Rock Identification Based on Laser-Induced Breakdown Spectroscopy Data in Tianwen-1 Pre-Flight Experiments

Abstract

Laser-induced breakdown spectroscopy (LIBS) coupled with chemometrics is an efficient method for rock identification and classification, which has considerable potential in planetary geology. A great challenge facing the LIBS community is the difficulty to accurately discriminate rocks with close chemical compositions. A convolutional neural network (CNN) model has been designed in this study to identify twelve types of rock, among which some rocks have similar compositions. Both the training set and the testing set are constructed based on the LIBS spectra acquired by Mars Surface Composition Detector (MarSCoDe) for China’s Tianwen-1 Mars exploration mission. All the spectra were collected from dedicated rock pellet samples, which were placed in a simulated Martian atmospheric environment. The classification performance of the CNN has been compared with that of three alternative machine learning algorithms, i.e., logistic regression (LR), support vector machine (SVM), and linear discriminant analysis (LDA). Among the four methods, it is on the CNN model that the highest classification correct rate has been obtained, as assessed by precision score, recall score, and the harmonic mean of precision and recall. Furthermore, the classification accuracy is inspected more quantitatively via Brier score, and the CNN is still the best performing model. The results demonstrate that the CNN-based chemometrics are an efficient tool for rock identification with LIBS spectra collected in a simulated Martian environment. Despite the relatively small sample set, this study implies that CNN-supported LIBS classification is a promising analytical technique for Tianwen-1 Mars mission and more planetary explorations in the future.