基于GEE云平台的小江流域泥石流迹地空间分布制图

doi:10.3964/j.issn.1000-0593(2025)04-1045-16

Abstract
References
Related Citation (15)

Download: PDF (55979 KB)
Export: BibTeX | EndNote (RIS)

Abstract Rapid, accurate and exhaustive research on the distribution of mudslide-hostile areas is of great significance, enabling us to understand and have a deep understanding of the scope of distribution of mudslides, the distribution pattern, the causes of the mudslides, and to further find scientific monitoring, prediction, prevention and management of the technical means by the specific situation, to reduce the problems and losses brought about by the mudslide disaster. To seek an efficient and high-precision method for extracting the spatial distribution of mudslides, this study chooses the Xiaojiang River Basin in Yunnan Province as the study area, employed the random forest algorithm based on the Google Earth Engine (GEE) platform to extract the spatial distribution of debris flow traces efficiently. Firstly, Four types of feature variables(spectral features, index features, topographic features, and texture features)were constructed using the 2022 Sentinel-2 image and topographic data, then the random forest feature variable importance score and the J-M distance were combined for the feature preference research and analysis, explored the importance of each feature variable on the extraction of mudslide traces, and finally, set up various feature combinations to create six schemes, compared and analyzed the accuracy of the debris flow traces extracted by the six experimental schemes, and found the best scheme to increase the recognition accuracy. The study shows that: (1) regardless of feature optimization, the accuracy of debris flow trace identification with the addition of terrain feature variables is higher than that with merely optical image data, indicating the utility of using terrain data for debris flow trace information extraction; (2) classification accuracy is affected differently by different feature variable kinds; topographic, index, texture, and spectral features are the feature types with the highest to lowest feature importance scores; (3)the experimental scheme 6 is the best results of the spatial distribution map of debris flow traces in Xiaojiang River Basin, Yunnan Province, in 2022, which constructed multi-dimensional feature variables and feature optimization based on the multi-source data of Sentinel-2 optical images and topographic data. This resulted in an overall accuracy of 94.95%, a Kappa coefficient of 0.94, a debris flow trace mapping accuracy of 91.01%, and a user accuracy of 95.29%. Furthermore, the scheme effectively reduced data redundancy while improving the classification accuracy. This study makes use of the Google Earth Engine (GEE) platform. These multi-source data combine topographic and optical remote sensing imagery and the Random Forest algorithm, which can quickly, accurately, and efficiently extract information on debris flow traces in areas with complex feature coverage over a large range of terrain and has a large potential for applications.

Key words：Debris flow traces identification; Feature optimization, J-M distance; Google Earth Engine; Sentinel-2 data; Random forest; Characteristic variables importance

Received: 2024-04-25 Accepted: 2024-10-10

ZTFLH:

P237

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

Cite this article:

ZONG Hui-lin,YUAN Xi-ping,GAN Shu, et al. Spatial Distribution Mapping of Debris Flow Site in Xiaojiang River Basin Based on the GEE Platform[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(04): 1045-1060.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)04-1045-16 OR https://www.gpxygpfx.com/EN/Y2025/V45/I04/1045

[1] ZHANG Liang-jie, GAN Shu, YUAN Xi-ping, et al(张良洁, 甘淑, 袁希平, 等). Journal of Lanzhou University(Natural Sciences)[兰州大学学报(自然科学版)], 2021, 57(1): 122.
[2] ZHANG Xiao-dong, LIU Xiang-nan, ZHAO Zhi-peng, et al(张晓东, 刘湘南, 赵志鹏, 等). The Chinese Journal of Geological Hazard and Control(中国地质灾害与防治学报), 2015, 26(3): 120.
[3] LI Liang, DONG Xu-bin, ZHAO Qing-hua(李梁, 董旭彬, 赵清华). Computer Engineering and Applications(计算机工程与应用), 2019, 55(21): 167.
[4] Zhao Yan, Meng Xingmin, Qi Tianjun, et al. Geomorphology, 2020, 359: 107125.
[5] ZHANG Xiong-hao, GAN Shu, YUAN Xi-ping, et al(张雄浩, 甘淑, 袁希平, 等). Journal of Yunnan University(Natural Sciences Edition)[云南大学学报(自然科学版)], 2020, 42(3): 499.
[6] ZHANG Hai-yang, ZHANG Yao, TIAN Ze-zhong, et al(张海洋, 张瑶, 田泽众, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43(2): 597.
[7] YAN Kai, CHEN Hui-min, FU Dong-jie, et al(闫凯, 陈慧敏, 付东杰, 等). National Remote Sensing Bulletin(遥感学报), 2022, 26(2): 310.
[8] Brown C F, Brumby S P, Guzder-Williams B, et al. Scientitic Data, 2022, 9: 251.
[9] Shi T T, Xu H Q. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(10): 4038.
[10] Haralick R M, Shanmugam K, Dinstein I. IEEE Transactions on Systems, Man, and Cybernetics, 1973, SMC-3(6): 610.
[11] Tassi A, Vizzari M. Remote Sensing, 2020, 12(22): 3776.
[12] Breiman Leo. Machine Learning, 2001, 45: 5.
[13] Wang Ming, Mao Dehua, Wang Yeqiao, et al. Remote Sensing, 2022, 14(13): 3191.
[14] NING Xiao-gang, CHANG Wen-tao, WANG Hao, et al(宁晓刚, 常文涛, 王浩, 等). National Remote Sensing Bulletin(遥感学报), 2022, 26(2): 386.
[15] ZHANG Lei, GONG Zhao-ning, WANG Qi-wei, et al(张磊, 宫兆宁, 王启为, 等). National Remote Sensing Bulletin(遥感学报), 2019, 23(2): 313.
[16] Belgiu M, Dragut L. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 114: 24.
[17] XIE Yi, WANG Jia-nan, LIU Yu(解毅, 王佳楠, 刘钰). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2024, 55(2): 231.
[18] Sen Rikta, Goswami Saptarsi, Chakraborty Basabi. Jeffries-Matusita Distance as A Tool for Feature Selection. International Conference on Data Science and Engineering (ICDSE), 2019, 15.
[19] ZHANG Meng, ZENG Yong-nian, ZHU Yong-sen(张猛, 曾永年, 朱永森). National Remote Sensing Bulletin(遥感学报), 2017, 21(3): 479.
[20] LIU Tong, REN Hong-rui(刘通, 任鸿瑞). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2022, 38(12): 189.