Quantitative Analysis of Soil Heavy Metals Based on LSSVM
LIN Xiao-mei1, HUANG Yu-tao1, LIN Jing-jun2*, TAO Si-yu1, CHE Chang-jin1
1. College of Electronics and Electrical Engineering, Changchun University of Technology, Changchun 130012, China
2. College of Mechanical and Electrical Engineering, Changchun University of Technology, Changchun 130012, China
Abstract:In order to improve the accuracy of soil quantitative analysis, the partial least squares (PLS) and least squares support vector machine (LSSVM) were combined with laser-induced plasma technology to analyze the Cu elements in the soil. Two characteristic lines of Cu Ⅰ 324.75 nm and Cu Ⅰ 327.40 nm were compared and analyzed, and Cu Ⅰ 324.75 nm was selected as the analytical line. Firstly, the experimental parameters were optimized. The relationship between laser energy, acquisition delay time and signal-to-noise ratio were compared. The optimal energy and optimal acquisition delay time were 90 mJ and 1 000 ns, respectively. Then, the characteristic spectra of five different concentrations of samples were collected under the optimal experimental conditions. The calibration model was established by standard internal method, PLS and LSSVM. By comparing the fitting coefficient, root mean square error and average relative error of the three models, the calibration model of the standard internal method had poor performance due to the influence of soil matrix effect and self-absorption effect. And the fitting degree did not meet the experimental requirements. The values of the root mean square error and the average relative error were too large to meet the accuracy and stability requirements of the experiment. The calibration model was calibrated with PLS. Compared with the standard internal method, the accuracy and stability of the calibration model were significantly improved. R2 was increased from 0.870 1 to 0.985 1. The root mean square error of the training set and the root mean square error of the prediction set were reduced to the order of 0.1 Wt%. But the decrease of the average relative error with PLS model can’t meet the experimental requirement. It indicated that PLS could improve the accuracy of the calibration model rather than the stability of the calibration model. The matrix effect and self-absorption effect of soil cannot be reduced. Compared with the former calibration models, the LSSVM calibration model has better accuracy and stability. The R2 increased to 0.997 6. The data points in the model were basically distributed on the fitted curve with good linear correlation. Compared with the standard internal method, the root mean square error of the LSSVM training set decreased from 3.448 8 Wt% to 0.018 7 Wt%. The root mean square error of the prediction set decreased from 1.280 7 Wt% to 0.149 1 Wt%. The average relative error reduced by 6.24 times. Compared with the PLS calibration model, the parameters of the LSSVM calibration model were greatly reduced. The average relative error reduced from 7.455 6% to 2.137%, which can meet the stability requirements. It shows that the LSSVM algorithm has advantages for improving the accuracy and stability of the calibration model. It can reduce the matrix effects and the self-absorption effects of soil.
Key words:Laser-induced plasma technology; Internal standard method; Partial least squares; Least squares support vector machine; Soil
林晓梅,黄玉涛,林京君,陶思宇,车长金. 基于LSSVM的土壤重金属定量分析[J]. 光谱学与光谱分析, 2020, 40(05): 1523-1527.
LIN Xiao-mei, HUANG Yu-tao, LIN Jing-jun, TAO Si-yu, CHE Chang-jin. Quantitative Analysis of Soil Heavy Metals Based on LSSVM. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(05): 1523-1527.
[1] DU Chuang, GAO Xun, SHAO Yan, et al(杜 闯, 高 勋, 邵 妍, 等). Acta Physica Sinica(物理学报), 2013, 62(4): 221.
[2] Guo L B, Zhu Z H, Li J M, et al. Optics Express, 2018, 26(3): 2634.
[3] Zhang G Y, Song H, Liu Y, et al. Optik, 2018, 165(5): 87.
[4] Ramli M, Khumaeni A, Kurniawan K H, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2017, 132(6): 8.
[5] Ferreira E C, Milori D, Ferreira E J, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2008, 63(10): 1216.
[6] Li K X, Zhou W D, Shen Q M, et al. Journal of Analytical Atomic Spectrometry, 2010, 25(9): 1475.
[7] GU Yan-hong, ZHAO Nan-jing, MA Ming-jun, et al(谷艳红, 赵南京, 马明俊, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(3): 982.
[8] Shakeel H, Haq S U, Abbas Q, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2018, 146(8): 101.
[9] Lin J J, Lin X M, Guo L B, et al. Journal of Analytical Atomic Spectrometry, 2018, 33(7): 1545.
[10] Jiang H, Dong L, J Benchi, et al. Journal of Applied Spectroscopy, 2017, 84(1): 103.
[11] Guo Y M, Deng L M, Yang X Y, et al. Journal of Analytical Atomic Spectrometry, 2017, 32(12): 2401.
[12] Robledo M A, Sobral H, Garcia V A. Spectrochimica Acta Part B: Atomic Spectroscopy, 2018, 144(6): 7.
[13] Lepore K H, Fassett C I, Breves E A, et al. Applied Spectroscopy, 2017, 71(4): 1.