联合SBAS-InSAR与ConvLSTM神经网络方法的红河断裂带北段震后滑坡易发性评价

doi:10.13474/j.cnki.11-2246.2026.0415

摘要/Abstract

摘要： 震后滑坡是断裂带附近区域的次生地质灾害,对人民生命和基础设施构成严重威胁。针对传统的滑坡易发性评价未考虑震后滑坡时空动态变化的问题,本文采用SBAS-InSAR技术与ConvLSTM神经网络模型,对红河断裂带北段漾濞Ms6.4级地震后滑坡易发性评价展开研究。首先,利用2021年1月—2025年1月204景Sentinel-1A升降轨影像获取时间序列的地表形变信息,并结合高分辨率光学影像进行滑坡识别;然后,采用地理探测器与皮尔逊相关系数对环境因子进行分析;最后,利用ConvLSTM神经网络模型对滑坡易发性进行等级划分,并与BP、LSTM与CNN神经网络模型评价结果进行对比。结果显示,ConvLSTM模型均方根误差与平均绝对误差均低于另外3种模型,模型AUC值为0.912,具备更高的精度和更优的性能;高风险以上区域集中在红河断裂带北段以西,沿维西至巍山断裂两侧10 km以内分布。该方法进一步提升了滑坡易发性的精度,能够对震后断裂带附近区域滑坡灾害防控提供数据支撑与技术参考。

关键词: InSAR, 滑坡灾害, 人工神经网络, 滑坡易发性评价, 红河断裂带

Abstract: Post-earthquake landslides are secondary geological hazards in areas adjacent to fault zones,posing a serious threat to human life and infrastructure.To address the limitation of traditional landslide susceptibility assessments,which generally fail to consider the spatiotemporal dynamics of post-earthquake landslides,this study employs SBAS-InSAR technology combined with a ConvLSTM neural network model to evaluate landslide susceptibility following the Ms6.4 Yangbi earthquake in the northern segment of the Honghe fault zone.Firstly,time-series surface deformation information is obtained from 204 Sentinel-1A ascending and descending orbit images acquired from January 2021 to January 2025.This is combined with high-resolution optical imagery for landslide identification.Secondly,environmental factors are analyzed using the geographical detector method and Pearson correlation analysis.Finally,the ConvLSTM neural network model is used to classify landslide susceptibility levels,and the results are compared with those of three other neural network models: BP,LSTM,and CNN.The results show that the root mean square error and mean absolute error of the ConvLSTM model are both lower than those of the other three models,and the model achieves an AUC value of 0.912,indicating higher accuracy and better performance.High-risk and above-risk areas are concentrated to the west of the northern segment of the Honghe fault zone,distributed within 10 km on both sides of the Weixi—Weishan fault.This method further improves the accuracy of landslide susceptibility assessment and can provide data support and technical reference for post-earthquake landslide disaster prevention and control in areas near fault zones.

Key words: InSAR, landslide hazards, artificial neural networks, landslide susceptibility assessment, Honghe fault zone

中图分类号:

P237

周昱辰, 喜文飞, 曹逸凡, 郭峻杞, 庄永在, 王瑞亭, 洪文玉. 联合SBAS-InSAR与ConvLSTM神经网络方法的红河断裂带北段震后滑坡易发性评价[J]. 测绘通报, 2026, 0(4): 104-111,133.

ZHOU Yuchen, XI Wenfei, CAO Yifan, GUO Junqi, ZHUANG Yongzai, WANG Ruiting, HONG Wenyu. Post-earthquake landslide susceptibility assessment in the northern segment of the Honghe fault zone using an integrated SBAS-InSAR and ConvLSTM neural networks approach[J]. Bulletin of Surveying and Mapping, 2026, 0(4): 104-111,133.

参考文献

[1] 殷跃平.中国地质灾害减灾战略初步研究[C]//2004地质灾害调查与监测技术方法现场研讨会论文集.[S.l.]:中国地质调查局,2004.
[2] 廖明生,唐婧,王腾,等.高分辨率SAR数据在三峡库区滑坡监测中的应用[J].中国科学:地球科学,2012,42(2):217-229.
[3] 张路,廖明生,董杰,等.基于时间序列InSAR分析的西部山区滑坡灾害隐患早期识别:以四川丹巴为例[J].武汉大学学报(信息科学版),2018,43(12):2039-2049.
[4] 石固林,徐浪,张璇钰,等.西山村滑坡时序形变的SBAS-InSAR监测[J].测绘科学,2021,46(2):93-98.
[5] 黄润秋.中国西部地区典型岩质滑坡机理研究[J].地球科学进展,2004,19(3):443-450.
[6] 李军霞,王常明,王钢城.基于组合赋权-未确知测度理论的滑坡危险性评价[J].岩土力学,2013,34(2):468-474.
[7] 喜文飞,成鑫,杨志全,等.基于SBAS-InSAR技术和BP神经网络的高位远程滑坡危险性分析研究[J].昆明理工大学学报(自然科学版),2024,49(3):65-74.
[8] REICHENBACH P,ROSSI M,MALAMUD B D,et al.A review of statistically-based landslide susceptibility models[J].Earth-Science Reviews,2018,180:60-91.
[9] 黄发明,叶舟,姚池,等.滑坡易发性预测不确定性:环境因子不同属性区间划分和不同数据驱动模型的影响[J].地球科学,2020,45(12):4535-4549.
[10] 周天游,刘畅,薛鹏,等.基于不同机器学习的震后滑坡易发性建模研究[J].自然灾害学报,2023,32(5):177-185.
[11] 周定义,左小清,喜文飞,等.联合SBAS-InSAR和PSO-BP算法的高山峡谷区地质灾害危险性评价[J].农业工程学报,2021,37(23):108-116.
[12] 苏志萍,杨成生,王子倩.结合负样本优化与机器学习模型的怒江洲峡谷段滑坡易发性评价[J].地球信息科学学报,2025,27(4):979-993.
[13] GUO JUNQI X W.Landslide hazard susceptibility evaluation based on SBAS-InSAR technology and SSA-BP neural network algorithm:a case study of Baihetan Reservoir Area[J].Journal of Mountain Science,2024,21(3):952-972.
[14] 刘坚,李树林,陈涛.基于优化随机森林模型的滑坡易发性评价[J].武汉大学学报(信息科学版),2018,43(7):1085-1091.
[15] 刘晓杰,赵超英,李滨,等.基于InSAR技术的甘肃积石山震区活动滑坡识别与动态形变监测[J].武汉大学学报(信息科学版),2025,50(2):297-312.
[16] ZHOU Chao,YIN Kunlong,CAO Ying,et al.Landslide susceptibility modeling applying machine learning methods:a case study from Longju in the Three Gorges Reservoir area,China[J].Computers ＆ Geosciences,2018,112:23-37.
[17] 黄龙,孙倩,胡俊.基于InSAR与随机森林的滑坡敏感性评价与误差改正[J].测绘通报,2022(10):13-20.
[18] 虢顺民,计凤桔,向宏发,等.红河活动断裂带:中国活断层研究专辑[M].北京:海洋出版社,2001.
[19] 李莹,高原.地震各向异性与地质构造揭示的红河断裂带分段性[J].中国科学:地球科学,2024,54(8):2458-2477.
[20] 孙庆山,李乐.利用重复微震估算红河断裂带北段深部滑动速率[J].地球物理学报,2020,63(2):478-491.
[21] 邵九明.基于PS-InSAR的红河断裂带北、中段地壳形变研究[D].昆明:云南师范大学,2018.
[22] 向宏发,韩竹军,虢顺民,等.红河断裂带大型右旋走滑运动与伴生构造地貌变形[J].地震地质,2004,26(4):597-610.
[23] BERARDINO P,FORNARO G,LANARI R,et al.A new algorithm for surface deformation monitoring based on small baseline differential SAR interferograms[J].IEEE Transactions on Geoscience and Remote Sensing,2002,40(11):2375-2383.
[24] REN Hongrui,FENG Xiaoman.Calculating vertical deformation using a single InSAR pair based on singular value decomposition in mining areas[J].International Journal of Applied Earth Observation and Geoinformation,2020,92:102115.
[25] 高宏伟.联合升降轨数据的InSAR二维形变提取方法[D].成都:成都理工大学,2022.
[26] 李德仁,廖明生,王艳.永久散射体雷达干涉测量技术[J].武汉大学学报(信息科学版),2004,29(8):664-668.
[27] WANG Jinfeng,LI Xinhu,CHRISTAKOS G,et al.Geographical detectors‐based health risk assessment and its application in the neural tube defects study of the Heshun Region,China[J].International Journal of Geographical Information Science,2010,24(1):107-127.
[28] 陈丹璐,孙德亮,文海家,等.基于不同因子筛选方法的LightGBM-SHAP滑坡易发性研究[J].北京师范大学学报(自然科学版),2024,60(1):148-158.
[29] 孔嘉旭,庄建琦,彭建兵,等.基于信息量和卷积神经网络的黄土高原滑坡易发性评价[J].地球科学,2023,48(5):1711-1729.
[30] 张晓东.基于遥感和GIS的宁夏盐池县地质灾害风险评价研究[D].北京:中国地质大学(北京),2018.
[31] 朱清华.基于RF和SVM模型的灞桥区地质灾害易发性评价[D].西安:西安科技大学,2019.
[32] CRUDEN D M,VARNES D J.Landslide types and processes[J].Special Report-National Research Council,Transportation Research Board,1996,247:36-75.
[33] FRATTINI P,CROSTA G,CARRARA A.Techniques for evaluating the performance of landslide susceptibility models[J].Engineering Geology,2010,111(1/2/3/4):62-72.