Determination of Molybdenum in Geological Ores by Laser-Induced Breakdown Spectroscopy (LIBS) with Support Vector Machine Regression (SVMR) and Data Preprocessing

Abstract

A support vector machine regression (SVMR) model that integrates data preprocessing was devised for the determination of Mo in molybdenum ores. To eliminate the negative effects of spectral fluctuations and improve the computational efficiency, the model processes original measurements through the following steps: denoising via wavelet transform smoothing (WTS), debaselining via adaptive iteratively reweighted penalized least squares (airPLS), main characteristic peak extraction, elimination of abnormal spectral data via the box plot method, and normalization via min-max scaling. In this study, 255 characteristic peaks were selected from 17,916 spectral datasets, and the total number of datasets after removing the outliers was 491. The calibration curve approach was used to establish a univariate model. The limit of detection of Mo was 0.0080 wt%. The R2 value of the calibration curve was 0.6675. Linear regression (LR) and SVMR were used to establish a multivariate analysis model. Compared to that of the calibration curve approach, the determination coefficients (R P 2) of LR and SVMR increased from 0.8034 to 0.9859 and 0.9941, respectively. The range of relative errors (REP) decreased from 0.21%–67.66% to 0.48%–18.46% and 2.65%–7.44%, respectively; the mean absolute error (MAEP) was decreased from 0.0173 wt% to 0.0048 and 0.0039 wt%, respectively; and the root mean square error (RMSEP) decreased from 0.0243 wt% to 0.0065 and 0.0042 wt%, respectively. These results indicate that the integration of SVMR with data preprocessing is suitable for the determination of Mo in molybdenum ores.