Near-Infrared Spectral Feature Selection of Water-Bearing Rocks Based on Mutual Information
ZHANG Xiu-lian1, 2, ZHANG Fang1, 2*, ZHOU Nuan1, 2, ZHANG Jing-jie1,2, LIU Wen-fang3, ZHANG Shuai1, 2, YANG Xiao-jie1, 2
1. State Key Laboratory for Geomechanics and Deep Underground Engineering, China University of Mining and Technology, Beijing 100083, China
2. School of Mechanics and Civil Engineering, China University of Mining and Technology, Beijing 100083, China
3. College of Resources and Civil Engineering, Northeastern University, Shenyang 110004, China
Abstract：The relationship between near-infrared spectroscopic measurements of rock and its water content does not follow simple linear correlations, preventing the direct use of classical correlation analysis. In the present paper, an experiment on the water migration in cliff conglomerates from the Mogao Grottoes was performed，and collected 51 pieces of near-infrared spectra from three different positions sample. These spectra cover the whole process of the conglomerate from the initial dry state to the saturated state; then we selected a combined N point smooth and baseline correction method (NPS+B-corr) to preprocess the original near-infrared spectrum. According to the spectral curve features at 1 450 and 1 950 nm of the strong absorption spectrum, six initial feature variables, namely Height, Full Width at Half Maximum (FWHM), Area, Left Half Width (LHW), Right Half Width (RHW), and (LHW/RHW), were extracted to establish the initial feature set. Simultaneously, the extracted spectral characteristic variables were normalized, and the curve of each spectral characteristic parameter and the change of water content were drawn according to the result of the processing, determine the water content level. Then，the correlation among the feature variables of the initial feature set should be screened to remove redundant features. The initial feature set is simplified to three characteristic variables: Height, LHW, RHW. Finally, based on mutual information, the Best Individual Feature and Maximal Information Coefficient methods were used to evaluate the relationship between samples’ spectral characteristic parameters and water content. We found that: (1) at wavelengths between approximately 1 450 and 1 930 nm, the near-infrared spectrum of the conglomerate has obvious absorption peaks, and the absorption peaks show a strong correlation with the change of water content, which indicates that spectral reflectance was significantly correlated with water content; (2) the relationship of primary spectral characteristic parameters with total water content can be described by an S-shaped function，water content can be divided into three states of dry, water-absorbing, and saturated; (3) The near-infrared spectral characteristics selected by the two information methods are not completely consistent. Based on the BIF method, the correlation between the characteristic variable at 1 450 nm and the rock moisture content ranks from right to left as right shoulder width, peak height, and left shoulder width; at 1 900 nm, the peak height, right shoulder width, and left shoulder width. Based on the MIC method, the correlation between the characteristic variables at 1 450 and 1 900 nm and the rock water content level from the highest to the lowest in the left shoulder width, peak height, and right shoulder width; (4) Decision tree analysis suggests that the MIC method achieves higher accuracy in identifying water content level than the BIF method.
Key words：Water-bearing rock; Near-infrared spectroscopy; Mutual information; Water migration
[1] Cen H, He Y. Trends in Food Science & Technology, 2007. 18(2): 83.
[2] David B L, Gregory P A. Soil Science Society of America Journal, 2002, 66: 722.
[3] Mouazen A M, Karoui R, De Baerdemaeker J, et al. Soil Science Society of America Journal, 2006，70(4): 1295.
[4] CHU Xiao-li（褚小立）. Molecular Spectroscopy Analytical Technology Combined With Chemometrics and Its Applications(结合化学计量学的分子光谱分析技术及其应用). Beijing: Chemical Industry Press(北京: 化学工业出版社), 2011. 264.
[5] Balabin R M, Smirnov S V. Analytica Chimica Acta, 2011, 692(1-2): 63.
[6] Vinh L T, Lee S, Park Y T, et al. Applied Intelligence, 2012, 37(1): 100.
[7] YAO Xu, WANG Xiao-dan, ZHANG Yu-xi, et al(姚 旭, 王晓丹, 张玉玺, 等). Control and Decision（控制与决策）, 2012, 27(2): 161.
[8] Reshef D N, Reshef Y A, Finucane H K, et al. Science, 2011，334(6062): 1518.
[9] LIANG Ji-ye, FENG Chen-jiao, SONG Peng(梁吉业，冯晨娇，宋 鹏). Chinese Journal of Computers(计算机学报), 2016，39(1): 1.
[10] HE Man-chao，ZHANG Guo-feng，ZHAO Jian（何满潮，张国锋，赵 健）. Chinese Patent（中国专利）：CN 102253181, 2011.
[11] ZHANG Fang, HU Zuo-le, HOU Xin-li, et al（张 芳, 户佐乐, 侯欣莉, 等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2019, 39(11): 3395.
