基于InSAR技术与随机森林算法的清江流域长阳西段滑坡危险性评价

孟小军; 邢昭

doi:10.11932/karst2025y001

基于InSAR技术与随机森林算法的清江流域长阳西段滑坡危险性评价

doi: 10.11932/karst2025y001

孟小军^1,,
邢昭²

1.
中国地质大学(武汉)环境学院, 湖北武汉 430074
2.
长江大学资源与环境学院, 湖北武汉 430100

基金项目: 鄂西山区典型顺层岩质边坡开挖条件下稳定性分析及影响范围预测研究（DQKJ2023-4）

详细信息

作者简介:
孟小军（1988－），男，高级工程师，博士研究生在读，主要从事水文地质环境地质类工作。E-mail：362757097@qq.com

中图分类号: P642.2；P237
计量
- 文章访问数: 18
- HTML浏览量: 3
- PDF下载量: 2
- 被引次数: 0
出版历程
- 收稿日期: 2024-11-01
- 录用日期: 2025-01-02
- 修回日期: 2024-12-20
- 网络出版日期: 2025-09-03
- 刊出日期: 2025-06-25

Landslide susceptibility assessment in the western Changyang section of the Qingjiang River Basin based on InSAR technology and random forest algorithm method

MENG Xiaojun^1
,,
XING Zhao²

1.
School of Environmental Studies, China University of Geosciences, Wuhan, Hubei 430074, China
2.
College of Resources and Environment, Yangtze University, Wuhan, Hubei 430100, China

摘要

摘要: 以清江流域长阳西段滑坡为研究对象，采用SBAS-InSAR技术与随机森林算法相结合的评价方法，以斜坡单元为评价单元，对研究区滑坡危险性进行科学评价。选取地形类、地质类、水文类、人类工程活动等四大类共计12个评价因子指标作为研究区滑坡危险性评价指标，采用随机森林模型评价滑坡危险性，考虑评价模型中滑坡数据时效性差、不准确等特点，利用最新Sentinel-1A雷达数据，采用SBAS-InSAR方法获取最新的地面变形数据替代传统评价模型中的滑坡数据，结果表明，基于InSAR技术与随机森林算法的滑坡危险性评估AUC值为0.90，精确度较高。该方法有效地提高了地质灾害危险性评估的准确度，可以为政府部门的防灾减灾工作提供更加高效的决策支撑。
- 滑坡 /
- SBAS-InSAR /
- 随机森林算法 /
- 危险性评估 /
- 清江
Abstract: The Qingjiang River Basin, a typical karst mid-mountain geomorphic region where carbonate rocks constitute 72% of the lithology, has been extensively influenced by long-term geological processes. Quaternary loose deposit layers, mixed with soil and rock, are extensively distributed along both banks. These layers exhibit poor stability and are prone to frequent landslide disasters, such as the Pianshan landslide and Maoping landslide. Traditional landslide susceptibility assessments typically rely on static historical data and linear models, such as the information content method and the Analytic Hierarchy Process (AHP). However, these approaches are limited in their ability to capture the nonlinear characteristics of landslide evolution. To improve the timeliness and accuracy of the assessment, this study integrates Small Baseline Subset-InSAR (SBAS-InSAR) surface deformation monitoring technology with the random forest machine learning algorithm to conduct dynamic landslide susceptibility assessments in Ziqiu town and Yuxiakou town, covering a total area of 251.89 km² in Changyang county, Hubei Province.Based on the landslide development patterns in the study area, this study selects 12 evaluation indicators from four categories—topography, geology, hydrology, and human engineering activities—as the landslide susceptibility indicators for the region. It employs the Random Forest model for comprehensive susceptibility assessment. Due to the poor timeliness and inaccuracy of landslide data in traditional evaluation models, the study utilizes the latest Sentinel-1A radar data and applies the SBAS-InSAR method to obtain up-to-date surface deformation data to replace the conventional landslide data. The interpretation results show that the central and western parts of the study area are predominantly characterized by subsidence points, with a small number of uplift points, while the eastern region exhibits a greater distribution of uplift points. The density of surface deformation points decreases from the southern to the northern part of the study area. Along the Qingjiang River, surface deformation points are more densely distributed. From the western part of the study area to Ziqiu Town, subsidence points dominate, while from Ziqiu town to the eastern part of the study area, uplift points are more prevalent. Most of the surface deformation points are located around towns and villages. In Yuxiakou town, both subsidence and uplift points are present, while Ziqiu town mainly features uplift points. The surface deformation points are mainly located in hard carbonate rock formations, with densely distributed deformation points typically found on both sides of fault zones. The rock mass on either side of the fault is subjected to intense compression, leading to fracturing, which forms a fractured zone. The uneven distribution of stress on both sides can easily trigger landslides. Additionally, the comparison of surface deformation points with other evaluation factors reveals that these points are predominantly distributed in areas with slopes ranging from 8° to 25°, elevation differences between 10 m and 30 m, and proximity to construction land such as houses and roads, where human engineering activities significantly influence surface deformation.The 12 evaluation indicators and SBAS-InSAR interpretation results were used as training datasets, and the random forest method was employed to assess landslide susceptibility. The importance of the evaluation factors, as determined by the random forest classification prediction model, indicated that Quaternary thickness and engineering geological rock groups were significantly more influential than the other factors. This suggests that when the surface deformation rate is used as an indicator to evaluate landslide susceptibility levels, geological factors are predominant. The hardness and stability of the rocks, as well as the thickness of the Quaternary deposit layers, determine the scale and severity of landslides induced by surface deformation. Factors such as the influence range of river systems, elevation difference, and slope have relatively high importance values. Within a certain influence range of river systems, water level fluctuations may significantly affect landslide stability. Areas with greater elevation differences and steeper slopes exhibit higher surface deformation rates, consequently increasing the probability of landslides. The remaining factors have little impact on the prediction results; except for the distance to the fault, all are related to human engineering activities. This suggests that when the surface deformation rate is used as an indicator for landslide susceptibility assessment, human engineering activities may alter certain original landforms and potentially trigger surface deformation and landslides, although their influence is relatively limited.The calculation results indicate that the areas classified as extremely high-risk and high-risk for landslide hazards in the western section of Changyang, within the Qingjiang River Basin, account for a substantial proportion, reaching 32.22%. These areas are mainly concentrated near Ziqiu town on the eastern side of the study area and along the banks of the Qingjiang River, which aligns well with the spatial distribution of historical landslides. The Quaternary deposit thickness, engineering geological rock groups, and river systems are identified as the dominant controlling factors for landslide susceptibility. Areas characterized by thicker Quaternary deposits, interbedded with soft and hard rock layers, and the distance proximity to rivers (within 200 meters) demonstrate significantly higher probability of landslides. The ROC curve analysis of the hazard assessment model shows that the random forest model incorporating InSAR technology can effectively capture landslide susceptibility, achieving a high AUC value of 0.90. This model exhibits strong predictive performance and reliability, providing a novel approach to landslide susceptibility assessment and valuable decision-making support for governmental disaster prevention and mitigation efforts.
- landslide /
- SBAS-InSAR /
- random forest algorithm method /
- disaster assessment /
- the Qingjiang River

HTML

图 1 研究区地理位置图

Figure 1. Geographical location map of the study area

下载: 全尺寸图片幻灯片

图 2 评价因子的重要性

Figure 2. Importance ranking of evaluation factors

下载: 全尺寸图片幻灯片

图 3 评价因子分级图

Figure 3. Grading of evaluation factors

下载: 全尺寸图片幻灯片

图 4 时空基线图

Figure 4. Time-position plot

下载: 全尺寸图片幻灯片

图 5 干涉像对图

Figure 5. Time-baseline plot

下载: 全尺寸图片幻灯片

图 6 随机森林实施步骤图

Figure 6. Implementation steps of random forest model

下载: 全尺寸图片幻灯片

图 7 基于InSRA解译的地表变形速率分布图

Figure 7. Distribution of surface deformation rates interpreted by InSAR

下载: 全尺寸图片幻灯片

图 8 基于InSAR技术的随机森林模型滑坡危险性分区图

Figure 8. Zonation map of landslide susceptibility based on the InSAR technology and random forest model

下载: 全尺寸图片幻灯片

图 9 随机森林模型ROC曲线图

Figure 9. ROC curve of random forest model

下载: 全尺寸图片幻灯片

表 1 数据源一览表

Table 1. Overview of data sources

数据名称	数据尺度	数据来源
Sentinel-1A	5 m×20 m	欧洲航天局
滑坡点信息	/	宜昌市地质灾害隐患点数据库
DEM	30 m	地理空间数据云平台（http://www.gscloud.cn/home）
高差、坡度和地形起伏度、地质构造、曲率	30 m	利用DEM数据处理得到
工程地质岩组	1∶50000	中国地质调查局1∶5万中国地质图（https://www.cgs.gov.cn/）
第四系厚度	1∶10000	野外调查
河流水系、道路与居民点	/	全国地理信息资源服务系统（https://www.webmap.cn/main. do?method=index）全国1∶25 万基础地理信息数据库。
土地利用、植被覆盖度	1∶10000	遥感解译

下载: 导出CSV

表 2 基于InSAR技术的随机森林模型危险性分区表

Table 2. Zonation table of landslide susceptibility based on the InSAR technology and random forest model

分区类型	分区面积/km²	灾害点/个	灾害密度/ 个·(100 km²)⁻¹
极高危险区	30.74	17	2.90
高危险区	50.42	21	2.19
中危险区	74.78	8	0.56
低危险区	95.95	2	0.11

下载: 导出CSV

参考文献(39)

[1]	张保军, 李振作, 程俊祥, 邓邦龙. 茅坪与新滩滑坡体变形机理类比研究[J]. 长江科学院院报, 2008(1): 40-43, 57. doi: 10.3969/j.issn.1001-5485.2008.01.011 ZHANG Baojun, LI Zhenzuo, CHENG Junxiang, DENG Banglong. Analogy study on deformation mechanism of Maoping and Xintan landslide[J]. Journal of Yangtze River Scientific Research Institute, 2008(1): 40-43, 57. doi: 10.3969/j.issn.1001-5485.2008.01.011
[2]	赵信文, 金维群, 彭轲, 常宏, 黎清华, 黎义勇, 薛永恒. 清江中游隔河岩库区偏山滑坡形成机制及稳定性分析[J]. 吉林大学学报(地球科学版), 2009, 39(5): 874-881. ZHAO Xinwen, JIN Weiqun, PENG Ke, CHANG Hong, LI Qinghua, XUE Yongheng. Formation mechanism and stability analysis of the pianshan landslide in geheyan reservoir area of the middle reaches of the Qingjiang River[J]. Journal of Jilin University(Earth Science Edition), 2009, 39(5): 874-881.
[3]	王娅美, 张紫昭, 张艳阳, 张全, 黄媚, 努尔加玛力·伊斯马依力, 吾木提汗·哈力汗. 基于多种组合模型的新疆巩留县滑坡危险性评价研究[J]. 工程地质学报, 2023, 31(4): 1375-1393. WANG Yamei, ZHANG Zizhao, ZHANG Yanyang, ZHANG Quan, HUANG Mei, NUERJIAMALI Yisimayili, WUMUTIHAN Halihan. Landslide risk assessment of GongLiu county in XinJiang based on multiple combination models[J]. Journal of Engineering Geology, 2023, 31(4): 1375-1393.
[4]	何萍, 丁原章. 基于CF多元回归模型的地震滑坡危险性研究: 以香港屯门为例[J]. 地震, 2013, 33(2): 52-62. doi: 10.3969/j.issn.1000-3274.2013.02.007 HE Ping, DING Yuanzhang. Study on seismic landslide hazard based on CF multiple regression model: A case study of Tuen Mun, Hong Kong[J]. Earthquake, 2013, 33(2): 52-62. doi: 10.3969/j.issn.1000-3274.2013.02.007
[5]	Kawagoe S, Kazama S, Sarukkalige P R. Probabilistic modelling of rainfall induced landslide hazard assessment[J]. Hydrol. Earth Syst. Sci. , 2010,14, 1047-1061.
[6]	王涛, 刘甲美, 栗泽桐, 辛鹏, 石菊松, 吴树仁. 中国地震滑坡危险性评估及其对国土空间规划的影响研究[J]. 中国地质, 2021, 48(1): 21-39. doi: 10.12029/gc20210102 WANG Tao, LIU Jiamei, LI Zetong, XIN Peng, SHI Jusong, WU Shuren. Seismic landslide hazard assessment of China and its impact on national territory spatial planning[J]. Geology in China, 2021, 48(1): 21-39. doi: 10.12029/gc20210102
[7]	WANG Haishan, XU Jian, TAN Shucheng, ZHOU Jinxuan. Landslide Susceptibility Evaluation Based on a Coupled Informative-Logistic Regression Model-Shuangbai County as an Example[J]. Sustainability, 2023, 15: 12449. doi: 10.3390/su151612449
[8]	任敬, 范宣梅, 赵程, 周礼, 窦向阳. 贵州省都匀市滑坡易发性评价研究[J]. 水文地质工程地质, 2018, 45(5): 165-172. REN Jing, FAN Xuanmei, ZHAO Cheng, ZHOU Li, DOU Xiangyang. Evaluation of the landslide vulnerability in Duyun of Guizhou Province[J]. Hydrogeology & Engineering Geology, 2018, 45(5): 165-172.
[9]	YANG Xiaojie, HAO Zhenli, LIU Keyuan, TAO Zhigang, SHI Guangcheng. An Improved Unascertained Measure-Set Pair Analysis Model Based on Fuzzy AHP and Entropy for Landslide Susceptibility Zonation Mapping[J]. Sustainability 2023, 15, 6205.
[10]	牛鹏飞. 基于综合指数模型的舟曲县滑坡易发性评价[D]. 石家庄: 河北地质大学, 2021. NIU Pengfei. Landslide susceptibility evaluation of Zhouqu County based on comprehensive index model[D]. Shijiazhuang: Hebei GEO university, 2021.
[11]	ZHAO Hongliang, YAO Leihua, MEI Gang, LIU Tianyu, NING Yuansong. A fuzzy comprehensive evaluation method based on AHP and entropy for a landslide susceptibility map[J]. Entropy, 2017, 19: 396. doi: 10.3390/e19080396
[12]	吉日伍呷, 田宏岭, 韩继冲. 基于不同机器学习算法的地震滑坡易发性评价: 以鲁甸地震为例[J]. 昆明理工大学学报(自然科学版), 2022, 47(2): 47-56. JIRI Wuga, TIAN Hongling, HAN Jichong. Evaluation of the susceptibility of earthquake landslides based on different machine learning algorithms : taking Ludian earthquake as an example[J]. Journal of Kunming University of Science and Technology(Natural Science), 2022.47(2): 47-56.
[13]	Roman-Herrera J C, Rodriguez-Peces M J, Garzon-Roca J. Comparison between Machine Learning and Physical Models Applied to the Evaluation of Co-Seismic Landslide Hazard[J]. Applied Sciences, 2023, 13(14), 8285.
[14]	方然可, 刘艳辉, 黄志全. 基于机器学习的区域滑坡危险性评价方法综述[J]. 中国地质灾害与防治学报, 2021, 32(4): 1-8. FANG Ranke, LIU Yanhui, HUANG Zhiquan. A review of the methods of regional landslide hazard assessment based on machine learning[J]. The Chinese Journal of Geological Hazard and Control, 2021, 32(4): 1-8.
[15]	Alessandro Ferretti, Alfio Fumagalli, Fabrizio Novali, Claudio Prati, Fabio Rocca, Alessio Rucci. A New A-gorithm for Processing Interferometric Data Stacks: SqueeSAR[J]. IEE Transactionson Geoscience and Remote Sensing, 2011, 49(9): 3460-3470. doi: 10.1109/TGRS.2011.2124465
[16]	马博, 朱杰勇, 刘帅, 杨得虎. 联合时序InSAR和滑坡灾害易发性的元阳县滑坡灾害隐患识别[J]. 地质灾害与环境保护, 2023, 34(3): 8-14. doi: 10.3969/j.issn.1006-4362.2023.03.003 MA Bo, ZHU Jieyong, LIU Shuai, YANG Dehu. Hidden landslide disaster identification in Yuanyang county with combined Time-series InSAR and landslide disasters susceptibility[J]. Journal of Geological Hazards and Environment Preservation, 2023, 34(3): 8-14. doi: 10.3969/j.issn.1006-4362.2023.03.003
[17]	杨犇, 缪海波, 马闯, 朱隆奇. 基于SBAS-InSAR技术的山早滑坡形变分析[J]. 水电能源科学, 2023, 41(8): 175-179. YANG Ben, MIAO Haibo, MA Chuang, ZHU Longqi. Deformation analysis of shanzao landslide based on SBAS-InSAR technology[J]. Water Resources and Power, 2023, 41(8): 175-179.
[18]	ZHANG Peng, GUO Zihao, GUO Shuangfeng, XIA Jin. Land subsidence monitoring method in regions of variable radar reflection characteristics by integrating PS-InSAR and SBAS-InSAR techniques[J]. RemoteSens, 2022, 14: 3265.
[19]	LI Genger, HU Bo, LI Hui, LU Feng. Early ldentifying and monitoring landslides in Guizhou Province with lnSAR and optical remote sensing[J]. Journal of Sensors, 2021, 6616745: 1-19.
[20]	Breiman L. Random Forests. Machine Learning. 2001, 45, 5−32.
[21]	王雪冬, 张超彪, 王翠, 朱永东, 王海鹏. 基于Logistic回归与随机森林的和龙市地质灾害易发性评价[J]. 吉林大学学报 (地球科学版), 2022, 52(6): 1957-1970. WANG Xuedong, ZHANG Chaobiao, WANG Cui, ZHU Yongdong, WANG Haipeng. Geological disaster susceptibility in Helong City based on logistic regression and random forest[J]. Journal of Jilin University(Earth Science Edition), 2022, 52(6): 1957-1970.
[22]	LIU Meiyu, XU Bing, LI Zhiwei, MAO Wenxiang, ZHU Yan, HOU Jingxin, LIU Weizheng. Landslide Susceptibility Zoning in Yunnan Province Based on SBAS-InSAR Technology and a Random Forest Model[J]. Remote Sens, 2023, 15: 2864. doi: 10.3390/rs15112864
[23]	Saha Sunil, Saha Anik, Roy Bishnu, Dhruv Bhardwaj, Barnali Kundu. Integrating the Particle Swarm Optimization (PSO) with Machine Learning Methods for Improving The Accuracy of The Landslide Susceptibility Model[J]. Earth Science lnformatics, 2022, 15: 2637-2662. doi: 10.1007/s12145-022-00878-5
[24]	石辉, 邓念东, 周阳. 随机森林赋权层次分析法的崩塌易发性评价[J]. 科学技术与工程, 2021, 21(25): 10613-10619. doi: 10.3969/j.issn.1671-1815.2021.25.008 SHI Hui, DENG Niandong, ZHOU Yang. Evaluation of Collapse Susceptibility Based on Random Forest Weighted Analytic Hierarchy Process[J]. Science Technology and Engineering, 2021, 21(25): 10613-10619. doi: 10.3969/j.issn.1671-1815.2021.25.008
[25]	CHEN Jianping, WANG Zepeng, CHEN Wei, WAN Changyuan, LIU Yunyan, HUANG Junjie. The influence of the selection of non-geological disasters sample spatial range on the evaluation of environmental geological disasters susceptibility: a case study of Liulin County[J]. Environmental Scienca and Pollution Research, 2023, 30: 44756-44772. doi: 10.1007/s11356-023-25454-2
[26]	DENG Hui, WU Xiantan, ZHANG Wenjiang, LIU Yansong, LI Weile, LI Xiangyu, ZHOU Ping, ZHUO Wenhao. Slope-Unit Scale Landslide Susceptibility Mapping Based on the Random Forest Model in Deep Valley Areas[J]. Remote Sensing, 2022, 14(17): 4245. doi: 10.3390/rs14174245
[27]	张向营, 张春山, 孟华君, 王雪冰, 赵伟康, 郑满城. 基于Random Forest和AHP的贵德县北部山区滑坡危险性评价[J]. 水文地质工程地质, 2018, 45(4): 142-149. ZHANG Xiangying, ZHANG Chunshan, MENG Huajun, WANG Xuebing, ZHAO Weikang, ZHEN Mancheng. Landslide hazard evaluation in the northern mountainous area of Guide County based on Random Forest and AHP[J]. Hydrogeology & Engineering Geology, 2018, 45(4): 142-149.
[28]	WANG Yue, WEN Haijia, SUN Deliang, LI Yuechen. Ouantitative Assessment of andslide Risk Based on Susceptibility Mapping Using Random Forest and CeoDetector[J]. Remnote Sens, 2021, 13(13): 2625. doi: 10.3390/rs13132625
[29]	Samuele Segoni, Veronica Tofani, Daniela Lagomarsino, Sandro Moretti. Landslide susceptibility of the Prato-istoia-Lucca provinces, Tuscany, ltaly[J]. Journal of Maps, 2016,12(S1):401-406.
[30]	LAI Chengguang, CHEN Xiaohon, WANG Zhaoli, XU Chongyu, YANG Bing. Rainfall-induced landslide susceptibility assessment using random forest weight at basin scale[J]. Hydrology Research, 2018, 49 (5): 1363–1378.
[31]	ZHANG Kaixiang, WU Xueling, NIU Ruiqing, YANG Ke, ZHAO Lingran. The assessment of landslide susceptibility mapping using random forest and decision tree methods in the Three Gorges Reservoir area, China[J]. Environmental Earth Sciences, 2017, 76: 405. doi: 10.1007/s12665-017-6731-5
[32]	WU Wenhuan, ZHANG Qiang, Singh Vijay P, WANG Gang, ZHAO Jiaqi, SHEN Zexi, SUN Shuai. A Data-Driven Model on Google Earth Engine for Landslide Susceptibility Assessment in the Hengduan Mountains, the Qinghai−Tibetan Plateau[J]. Remote Sens, 2022, 14(18): 4662. doi: 10.3390/rs14184662
[33]	曾斌, 吕权儒, 寇磊, 艾东, 许汇源, 袁晶晶. 基于Logistic回归和随机森林的清江流域长阳库岸段堆积层滑坡易发性评价[J]. 中国地质灾害与防治学报, 2023, 34(4): 105-113. ZENG Bin, LYU Quanru, KOU Lei, AI Dong, XU Huiyuan, YUAN Jingjing. Susceptibility assessment of colluvium landslides along the Changyang section of Qingjiang River using Logistic regression and random forest methods[J]. The Chinese Journal of Geological Hazard and Control, 2023, 34(4): 105-113.
[34]	王本栋, 李四全, 许万忠, 杨勇, 李永云. 基于3种不同机器学习算法的滑坡易发性评价对比研究[J]. 西北地质, 2024, 57(1): 34-43. doi: 10.12401/j.nwg.2023033 WANG Bendong, LI Siquan, XU Wanzhong, YANG Yong, LI Yongyun. A Comparative Study of Landslide Susceptibility Evaluation Based on Three Different Machine Learning Algorithms[J]. Northwestern Geology, 2024, 57(1): 34-43. doi: 10.12401/j.nwg.2023033
[35]	曾斌, 刘诗雅, 董琦, 袁晶晶, 艾东. 联合PS-InSAR和SBAS-InSAR的鄂西山区滑坡隐患识别: 以长阳县清江流域为例[J]. 安全与环境工程, 2024, 31(2): 202-212. ZENG Bin, LIU Shiya, DONG Qi, YUAN Jingjing, AI Dong. Identification of landslide hazards in western Hubei mountainous area by combining PS-InSAR and SBAS-InSAR: Taking Qingjiang River Basin of Changyang County as an example[J]. Safety and Environmental Engineering, 2024, 31(2): 202-212.
[36]	吴孝情, 赖成光, 陈晓宏, 任秀文. 基于随机森林权重的滑坡危险性评价: 以东江流域为例[J]. 自然灾害学报, 2017, 26(5): 119-129. WU Xiaoqing, LAI Chengguang, CHEN Xiaohong, REN Xiuwen. A landslide hazard assessment based on random forest weight: a case study in the Dongjiang River Basin[J]. Journal of Natural Disasters, 2017, 26(5): 119-129.
[37]	王超. 基于机器学习的滑坡危险性评价研究[D]. 成都: 电子科技大学, 2022. WANG Chao. Study on Risk Assessment of Landslide Based on Machine Learning[D]. Chengdu: University of Electronic Science and Technology of China, 2022.
[38]	王璨, 肖浩, 肖婷, 方亚其, 刘磊磊. 基于机器学习的长沙市滑坡灾害快速风险评价[J]. 矿冶工程, 2023, 43(5): 26-31, 36. WANG Can, XIAO Hao, XIAO Ting, FANG Yaqi, LIU Leiei. Efficient Risk Assessment of Landslide Disasters in Changsha City Based on Machine Learning[J]. Mining and Metallurgical Engineering, 023, 43(5): 26-31, 36.
[39]	戴勇, 孟庆凯 , 陈世泷, 李威, 杨立强. 基于BPNN-SHAP模型的滑坡危险性评价: 以伊犁河流域为例[J]. 沉积与特提斯地质, 2024, 44(3): 534-546. DAI Yong, MENG Qingkai, CHEN Shilong, LI Wei, YANG Liqiang. Landslide hazard evaluation based on BPNN-SHAP model: A case study of the Yili River Basin, Xinjiang Province[J]. Sedimentary Geology and Tethyan Geology, 2024, 44(3): 534-546.