Identification of Sandstone Lithology Based on Hyperspectral Combined With Support Vector Machine Algorithm
JIAO Long1, LI Ying1, TONG Rong-chao2, WANG Cai-ling3
1. College of Chemistry and Chemical Engineering, Xi'an Shiyou University, Xi'an 710065, China
2. College of Computer Science, Xi'an Shiyou University, Xi'an 710065, China
3. Downhole Technology Service Company, CNPC Bohai Drilling Engineering Limited, Tianjin 300283, China
Abstract：Accurate identification of sandstone lithology is crucial in resource exploration, geological engineering, and building material research. Hyperspectral is an emerging analytical method with the advantages of spectral integration, a large amount of information, fast analysis speed, and non-destructive testing. It overcomes the problems of long time and complex procedures of traditional analytical methods. The support vector machine (SVM) method has strong learning and generalization ability, and is a fast and accurate analysis method. Therefore, hyperspectral analysis combined with support vector machine modeling established the identification method of different lithological sandstones. Four types of sandstone samples with different lithologies were collected, and their hyperspectral data were collected. Hyperspectral data were preprocessed by standard normal variable transformation (SNV), multiple scattering correction (MSC), and Savitzky-Golay smoothing method (SG), respectively. After that, partial least squares discriminant analysis (PLS-DA) and SVM methods were used to establish classification models. In the SVM model, the Gaussian kernel function (RBF kernel) is selected to establish the SVM classification model. The grid search method optimizes the penalty parameter C and the kernel function gamma parameter in the SVM. The value of C is determined to be (0.1, 1, 10, 100), and the radial basis function gamma parameter is (0.01, 0.1, 1, 10). 16 parameter combinations are formed, and the classification models are established respectively. The five-fold cross-validation classification accuracy of the best PLSDA and SVM models reaches 93.20% and 96.40%. The best MSC-PLSDA and SNV-SVM models established can accurately identify the test set samples. The classification accuracy of the test set of the MSC-PLSDA model reaches 89.00%, and the corresponding F1 values reach more than 80%. The classification accuracy of the test set of the MSC-SVM model reaches 96%, and the corresponding F1 value of the model reaches more than 90%. Among them, the recognition accuracy of argillaceous and fine-grained sandstone is the highest, and the F1 value reaches 100%. The results show that hyperspectral technology combined with the support vector machine method is a reliable method for sandstone lithology identification and analysis, and the spectral preprocessing method has a significant impact on the identification accuracy, which provides a new idea for sandstone lithology identification and analysis systems.
Key words：Hyperspectral; Support vector Machine; Sandstone; Lithology identification
焦 龙，李 莹，仝容超，王彩玲. 高光谱结合支持向量机算法的砂岩岩性识别[J]. 光谱学与光谱分析, 2025, 45(09): 2496-2501.
JIAO Long, LI Ying, TONG Rong-chao, WANG Cai-ling. Identification of Sandstone Lithology Based on Hyperspectral Combined With Support Vector Machine Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2496-2501.
[1] FU Guang-ming, YAN Jia-yong, ZHANG Kun, et al(付光明, 严加永, 张 昆, 等). Progress in Geophysics(地球物理学进展), 2017, 32(1): 26.
[2] Wang C R, Li P J, Long Q Q, et al. Minerals, 2024, 14(3): 275.
[3] Xu Z, Shi H, Lin P, et al. Journal of Petroleum Science and Engineering, 2021, 205(1): 108853.
[4] Liu H, Wu K, Xu H, et al. Remote Sensing, 2021, 13(16): 3117.
[5] Wang J, Cao J X. IEEE Geoscience and Remote Sensing Letters, 2021, 20: 7506405.
[6] Song Z Y, Kuenzer C. International Journal of Coal Geology, 2017, 171: 142.
[7] Wang Z Y, Tian S F. Microprocessors and Microsystems, 2021, 87: 104394.
[8] Zhong Y F, Wang X Y, Xu Y, et al. IEEE Geoscience and Remote Sensing Magazine, 2018, 6(4): 46.
[9] Su X, Wang Y, Mao J, et al. Journal of Intelligent & Robotic Systems, 2022, 105(4): 75.
[10] Paoletti M E, Haut J M, Pereira N S, et al. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(12): 10378.
[11] WANG Jun-jie, YUAN Xi-ping, GAN Shu, et al(王俊杰, 袁希平, 甘 淑, 等). Journal of Lanzhou University(Natural Sciences)[兰州大学学报(自然科学版)], 2023, 59(6): 786.
[12] HU Cheng-hao, WU Wen-yuan, MIAO Ying, et al(胡程浩, 吴文渊, 苗 莹, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2024, 44(3): 784.
[13] YE Fa-wang, MENG Shu, ZHANG Chuan, et al(叶发旺, 孟 树, 张 川, 等). Journal of Geo-information Science(地球信息科学学报), 2019, 21(2): 279.
[14] Melgani F, Bruzzone L. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(8): 1778.
[15] Zhang X, Sun J, Li P, et al. LWT-Food Science and Technology, 2021, 152(5): 112295.
[16] Zhang P P, Shen B B, Ji H W, et al. Food Analytical Methods, 2022, 15(5): 1397.
[17] Wang K, Cheng L G, Yong B. Remote Sensing, 2020, 12(13): 2154.
[18] Yang H Q, Kuang B Y, Mouazen A M. Advanced Materials Research, 2011, 181-182: 416.
[19] Helin R, Indahl U G, Tomic O, et al. Journal of Chemometrics, 2022, 36(2): e3374.
[20] Grisanti E, Totska M, Huber S, et al. Journal of Spectroscopy, 2018, 2018: 5037572.
[21] Chen H Z, Song Q, Tang G Q, et al. ISRN Spectroscopy, 2015, 2013: 642190.
[22] Xie L, Ying Y, Ying T, et al. Analytica Chimica Acta, 2007, 584(2): 379.
[23] Bozic D, Runje B, Lisjak D, et al. Applied Sciences, 2023, 13(14): 8187.
[24] DU Yuan-sheng, YU Wen-chao, WENG Shen-fu, et al(杜远生, 余文超, 翁申富, 等). Journal of Palaeogeography(Chinese Edition)(古地理学报), 2024, 26(5): 1152.
