禄丰恐龙谷三种典型沉积岩的高光谱响应特征分析及识别模型方法研究

doi:10.3964/j.issn.1000-0593(2023)09-2855-07

Abstract
References
Related Citation (15)

Download: PDF (6379 KB)
Export: BibTeX | EndNote (RIS)

Abstract Hyperspectral remote sensing technology can show the spectral characteristics of rocks and minerals in more detail, which provides a powerful means for hyperspectral rock and mineral identification. The traditional hyperspectral rock and mineral identification model based on specific absorption characteristic band depends on high a priori knowledge and is difficult to meet the requirements of distinguishing different types of rocks. Therefore, exploring and establishing an accurate and efficient hyperspectral rock automatic identification model is of great significance. Three typical sedimentary rocks (21 mudstone, sandstone and limestone) were collected as target samples in the Lufeng Dinosaur Valley area. The hyperspectral data of sedimentary rock samples in the range of 350~2 500 nm were obtained with the aid of the ASD fieldspec3 ground feature spectrometer. The original spectrum's first-order differential and continuous removal transformation were carried out, and the spectral characteristics were analyzed. The continuous projection algorithm (SPA) was used. Competitive adaptive reweighted sampling algorithm (CARS) and iterative retained information variable method (IRIV) select the characteristic wavelengths in the original spectrum and transformed spectrum and then establish support vector machine (SVM) and random forest (RF) recognition models based on the full band and characteristic wavelength data respectively. The results show that the three feature variable selection algorithms have a good dimensionality reduction effect on hyperspectral data, and the number of feature wavelengths selected from the original spectrum and the two transform spectra is between 7~59. It is obtained that the combined continuum removal SPA-SVM model method performs best for identifying three types of target sedimentary rocks, and its recognition accuracy is 0.952 4. At this time, 10 characteristic wavelengths are selected for the input model, which accounts for only 0.5% of the whole band, which greatly reduces the amount of calculation of the model. Two characteristic wavelengths are located in the Fe²⁺ and Fe³⁺ absorption bands near 550 nm, Two Fe³⁺ absorption bands near 900nm and five water molecules and hydroxyl absorption bands near 1 900，and 2 200 nm can better reflect the spectral absorption characteristics caused by the difference of chemical composition of sedimentary rocks. The experimental results show that the automatic recognition of hyperspectral sedimentary rocks using spectral transformation and characteristic variable selection algorithm is feasible and can provide a reference for hyperspectral rock and mineral recognition methods.

Key words：Hyperspectral; Sedimentary rock; Spectral analysis; Characteristic wavelength selection; Support vector machine

Received: 2022-04-18 Accepted: 2022-11-01

ZTFLH:

P237

Corresponding Authors: GAN Shu E-mail: gs@kust.edu.cn

Cite this article:

WANG Jun-jie,YUAN Xi-ping,GAN Shu, et al. Hyperspectral Identification Method of Typical Sedimentary Rocks in Lufeng Dinosaur Valley[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2855-2861.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2023)09-2855-07 OR https://www.gpxygpfx.com/EN/Y2023/V43/I09/2855

[1] ZHANG Cheng-ye, QIN Qi-ming, CHEN Li, et al(张成业, 秦其明, 陈理，等). Optics and Precision Engineering(光学精密工程), 2015, 23(8): 2407.
[2] Schneider S, Murphy R J, Melkumyan A. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 98: 145.
[3] Kumar C, Chatterjee S, Oommen T, et al. International Journal of Applied Earth Observation and Geoinformation, 2020, 86: 102006.
[4] GAN Fu-ping, WANG Run-sheng，MA Ai-nai, et al(甘甫平，王润生，马蔼乃，等). Earth Science Frontiers(地学前缘), 2003，(2): 445.
[5] LIU Li-xin, HE Di, LI Meng-zhu, et al(刘立新，何迪，李梦珠，等). Chinese Journal of Lasers(中国激光), 2020, 47(11): 291.
[6] LI Guan-wen, GAO Xiao-hong, XIAO Neng-wen, et al(李冠稳，高小红，肖能文，等). Acta Optica Sinica(光学学报), 2019, 39(9): 361.
[7] Lin H, Shu G, Xiping Y, et al. Earth Science Informatics, 2022, 15(1): 455.
[8] WANG Liu-san, HUANG Zi-liang, WANG Ru-jing(汪六三，黄子良，王儒敬). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2021, 52(6): 361.
[9] XU Nian-xu, TIAN Qing-jiu, SHEN Huai-fei, et al(徐念旭，田庆久，申怀飞，等). Remote Sensing for Natural Resources(自然资源遥感)，2018, 30(4): 28.
[10] YAN Xin-fang, GAN Shu, HU Lin, et al(闫馨芳，甘淑，胡琳，等). Science of Surveying and Mapping(测绘科学), 2021, 46(7): 60.
[11] GUO Wen-chuan, ZHU De-kuan, ZHANG Qian, et al(郭文川，朱德宽，张乾，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2020, 51(9): 350.
[12] ZHANG Xu-hui, ZHANG Kai-xin, ZHANG Chao, et al(张旭辉，张凯新，张超，等). Journal of Xi'an University of Science and Technology(西安科技大学学报), 2020, 40(5): 760.
[13] YU Lei, ZHANG Tao, ZHU Ya-xing, et al(于雷，张涛，朱亚星，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2018, 34(16): 148.
[14] Xu Y, Wang J, Xia A, et al. Remote Sensing, 2019, 11(3): 254.
[15] WANG Shan-shan, ZHOU Ke-fa, WANG Jin-lin, et al(王珊珊，周可法，王金林，等). Chinese Journal of Geology(地质科学), 2015, 50(4): 1261.