An Improved Sub-Model PLSR Quantitative Analysis Method Based on SVM Classifier for ChemCam Laser-Induced Breakdown Spectroscopy

Abstract

Laser-induced breakdown spectroscopy (LIBS) is a powerful tool for qualitative and quantitative analysis. Component analysis is a significant issue for the LIBS instrument onboard the Mars Science Laboratory (MSL) rover Curiosity ChemCam and SuperCam on the Mars 2020 rover. The partial least squares (PLS) sub-model strategy is one of the outstanding multivariate analysis methods for calibration modeling, which is firstly developed by the ChemCam science team. We innovatively used a support vector machine (SVM) classifier to select the corresponding sub-model. Then conventional regression approaches partial least squares regression (PLSR) was utilized as a sub-model to prove that our selecting method was feasible, effective, and well-performed. For eight oxides, i.e., SiO2, TiO2, Al2O3, FeOT, MgO, CaO, Na2O, and K2O, the modified SVM-PLSR blended sub-model method was 34.8% to 62.4% lower than the corresponding root mean square error of prediction (RMSEP) of the full model method. In order to avoid that SVM classifiers classifying the spectrum into an incorrect class, an optimized method was proposed which worked well in the modified PLSR blended sub-models.

A hybrid wavelength selection strategy-based quantitative analysis model for LIBS data from standard ground samples of the Curiosity rover on Mars

“…The results predicted by the SVM model were more accurate at higher concentrations because the SVM method models the nonlinear effects caused by self-absorption well. 65 Therefore, our results indicate that the hybrid wavelength screening strategy combined with SVM was the optimal prediction model in this work. In the quantitative analysis of the elements, screening the spectral information used the effective spectral information fully while reducing the effect of the fluctuations and the matrix effect, thereby improving the precision of the quantitative analysis model.…”

Improving quantitative analysis of cement elements in laser-induced breakdown spectroscopy through combining matrix matching with regression

“…To deal with the above issue, a practical approach is matrix matching, wherein samples are segregated into different groups based on different types of sample matrices. Current research primarily employs methodologies, such as traditional machine learning classiers, [22][23][24] and adaptive subset matching (ASM), 25 to group the samples. An individual model is then built for each group of samples, and multiple models are used to improve the accuracy of quantication.…”

“…22,23 Similar studies further consider the similarity of sample matrix properties and the optimization of multiple regression models. 24,25 In the aforementioned studies, the sample division process is based on supervised learning, which requires prior or auxiliary category information. Such a requirement can be avoided by using clustering analysis instead of classiers in the sample division process.…”