基于时序InSAR与BiGRU的库岸滑坡形变分析与预测

doi:10.13474/j.cnki.11-2246.2026.0109

测绘通报 ›› 2026, Vol. 0 ›› Issue (1): 51-56.doi: 10.13474/j.cnki.11-2246.2026.0109

基于时序InSAR与BiGRU的库岸滑坡形变分析与预测

刘艺梁^1,2,3, 李永奕^1,2,3, 朱前^1,2,3, 左清军^1,2,3, 樊西丰^1,2,3, 宋琨^1,2,3, 申高伟^1,2,3, 汤罗圣⁴

1. 湖北长江三峡滑坡国家野外科学观测研究站, 湖北宜昌 443002;
2. 防灾减灾湖北省重点实验室, 湖北宜昌 443002;
3. 三峡大学土木与建筑学院, 湖北宜昌 443002;
4. 湖北省交通规划设计院股份有限公司, 湖北武汉 430051

收稿日期:2025-05-27 发布日期:2026-02-03
通讯作者: 李永奕。E-mail:1300839556@qq.com
作者简介:刘艺梁(1985—),男,博士,副教授,研究方向为库岸地质灾害遥感识别与监测预警。E-mail:lyl@ctgu.edu.cn
基金资助:
国家自然科学基金(41807294);防灾减灾湖北省重点实验室开放基金(2025KJZ02);湖北省交通运输厅科技项目(2023-121-4-2);三峡大学土木与建筑学院科研创新基金(2024SSCX003);湖北省科技计划(2025CSA068)

Analysis and prediction of reservoir bank landslide deformation based on time series InSAR and BiGRU

LIU Yiliang^1,2,3, LI Yongyi^1,2,3, ZHU Qian^1,2,3, ZUO Qingjun^1,2,3, FAN Xifeng^1,2,3, SONG Kun^1,2,3, SHEN Gaowei^1,2,3, TANG Luosheng⁴

1. National Field Observation and Research Station of Landslides in Three Gorges Reservoir Area of Yangtze River, Yichang 443002, China;
2. Hubei Key Laboratory of Disaster Prevention and Mitigation, Yichang 443002, China;
3. College of Civil Engineering & Architecture, China Three Gorges University, Yichang 443002, China;
4. Hubei Provincial Communications Planning and Design Institute Co., Ltd., Wuhan 430051, China

Received:2025-05-27 Published:2026-02-03

摘要/Abstract

摘要： 三峡库区受地质构造与水库蓄水影响,滑坡灾害频发,准确的监测与预测滑坡形变对保障区域安全至关重要。针对传统监测方法在大范围、高精度形变监测方面的局限性,本文利用2021年1月至2023年12月的73景Sentinel-1A升轨影像数据,采用斯坦福永久散射体(StaMPS)技术获取了三峡库区三门洞滑坡的地表形变信息,通过筛选高相干性控制点分析滑坡变形特征,并结合全球导航卫星系统(GNSS)数据进行验证。同时,采用ARIMA模型与CNN-BiGRU-Attention模型,对高形变区控制点位移进行预测。结果表明:三门洞滑坡前缘及中部为高形变区,形变速率介于-108.9～-43.9 mm/a;组合预测模型均方根误差为1.11 mm,平均绝对误差为0.97 mm,显著提升了预测精度,为地质灾害智能预警提供了新的技术方案。

关键词: 时序InSAR, StaMPS, 库岸滑坡, 形变分析, 预测模型

Abstract: Due to the influence of geological structure and reservoir storage,landslides are frequent in the Three Gorges Reservoir area.Accurate monitoring and prediction of landslide deformation is crucial to ensuring regional safety.Due to the limitations of traditional methods for monitoring large-scale,high-precision deformation,this paper uses 73 Sentinel-1A up-orbit images from January 2021 to December 2023 and the Stanford method for persistent scatterers (StaMPS) technique to analyze the Sanmendong landslide's surface deformation in the Three Gorges Reservoir area.We systematically analyze the landslide deformation characteristics by screening the highly coherent control points and introduce global navigation satellite system (GNSS) data for validation.At the same time,we combine the ARIMA model with the CNN-BiGRU-Attention model to predict the displacement of the control points in the highly deformed area.The results show that the leading edge and middle part of the Sanmendong landslide are high-deformation areas with deformation rates ranging from -108.9 to -43.9 mm/a.The combined prediction model's RMSE is 1.11 mm and its MAE is 0.97 mm.It significantly improves the prediction accuracy and provides a new technical solution for intelligent early warning of geologic hazards.

Key words: time series InSAR, StaMPS, bank landslide, deformation analysis, prediction model

中图分类号:

P237

刘艺梁, 李永奕, 朱前, 左清军, 樊西丰, 宋琨, 申高伟, 汤罗圣. 基于时序InSAR与BiGRU的库岸滑坡形变分析与预测[J]. 测绘通报, 2026, 0(1): 51-56.

LIU Yiliang, LI Yongyi, ZHU Qian, ZUO Qingjun, FAN Xifeng, SONG Kun, SHEN Gaowei, TANG Luosheng. Analysis and prediction of reservoir bank landslide deformation based on time series InSAR and BiGRU[J]. Bulletin of Surveying and Mapping, 2026, 0(1): 51-56.

参考文献

[1] 殷坤龙,朱良峰.滑坡灾害空间区划及GIS应用研究[J].地学前缘,2001,8(2):279-284.
[2] 叶润青,付小林,郭飞,等.三峡水库运行期地质灾害变形特征及机制分析[J].工程地质学报,2021,29(3):680-692.
[3] 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.
[4] ZEBKER H A,GOLDSTEIN R M.Topographic mapping from interferometric synthetic aperture radar observations[J].Journal of Geophysical Research:Solid Earth,1986,91(B5):4993-4999.
[5] ZHAO Chaoying,KANG Ya,ZHANG Qin,et al.Landslide identification and monitoring along the Jinsha River Catchment (wudongde reservoir area),China,using the InSAR method[J].Remote Sensing,2018,10(7):993.
[6] 刘艺梁,樊西丰,申高伟,等.基于时序InSAR技术的木鱼包滑坡时空变形特征分析[J].地质科技通报,2025,44(2):78-93.
[7] 张伟斌,金永新,袁本银.基于BeiDou/GPS双系统的三峡滑坡监测预警系统[J].测绘通报,2013(2):120-121.
[8] 王晨辉,赵贻玖,郭伟,等.滑坡位移EEMD-SVR预测模型[J].测绘学报,2022,51(10):2196-2204.
[9] 李达,瞿伟,张勤,等.融合多层感知机和优化支持向量回归的滑坡位移预测模型[J].武汉大学学报(信息科学版),2023,48(8):1380-1388.
[10] 刘媛媛,陈人杰,陈能辉.西藏色拉滑坡时序InSAR二维形变反演与预测[J].北京理工大学学报,2023,43(11):1115-1124.
[11] ZHOU Chao,CAO Ying,GAN Lulu,et al.A novel framework for landslide displacement prediction using MT-InSAR and machine learning techniques[J].Engineering Geology,2024,334:107497.
[12] YU Chen,PENNA N T,LI Zhenhong.Generation of real-time mode high-resolution water vapor fields from GPS observations[J].Journal of Geophysical Research:Atmospheres,2017,122(3):2008-2025.
[13] YU Chen,LI Zhenhong,PENNA N T,et al.Generic atmospheric correction model for interferometric synthetic aperture radar observations[J].Journal of Geophysical Research:Solid Earth,2018,123(10):9202-9222.
[14] YU Chen,LI Zhenhong,PENNA N T.Interferometric synthetic aperture radar atmospheric correction using a GPS-based iterative tropospheric decomposition model[J].Remote Sensing of Environment,2018,204:109-121.
[15] 朱建军,胡俊,李志伟,等.InSAR滑坡监测研究进展[J].测绘学报,2022,51(10):2001-2019.
[16] USAI S,KLEES R.SAR interferometry on a very long time scale:a study of the interferometric characteristics of man-made features[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(4):2118-2123.
[17] HOOPER A,BEKAERT D,SPAANS K,et al.Recent advances in SAR interferometry time series analysis for measuring crustal deformation[J].Tectonophysics,2012,514:1-13.
[18] GE Qi,SUN Hongyue,LIU Zhongqiang,et al.A data-driven intelligent model for landslide displacement prediction[J].Geological Journal,2023,58(6):2211-2230.
[19] GE Qi,LI Jin,LACASSE S,et al.Data-augmented landslide displacement prediction using generative adversarial network[J].Journal of Rock Mechanics and Geotechnical Engineering,2024,16(10):4017-4033.
[20] 汪洋,殷坤龙,安关峰.滑坡敏感因子的灰色关联分析[J].岩土力学,2004,25(1):91-93.

基于时序InSAR与BiGRU的库岸滑坡形变分析与预测

Analysis and prediction of reservoir bank landslide deformation based on time series InSAR and BiGRU

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李景洮, 张双成, 盛磊, 张毅, 强菲, 聂腾, 刘宁, 闻繁. 时序InSAR与普适型GNSS用于西安地面沉降监测研究[J]. 测绘通报, 2026, 0(1): 18-24,46.
[2]	张昱鑫, 袁希平, 甘淑, 彭翔, 王松. 时序InSAR技术在矿区地表沉降监测与时空演化分析中的应用[J]. 测绘通报, 2025, 0(3): 15-20.
[3]	张双成, 李思洁子, 任志鹏, 司锦钊, 胡兴群. 融合时序InSAR与ESMD的高填方膨胀土机场隐患识别与形变监测[J]. 测绘通报, 2025, 0(3): 39-45.
[4]	严胜航, 李素敏, 郭军, 宋昱霏, 沈显名. 基于多源遥感的巨型滑坡四维特征解译——以糯勒滑坡为例[J]. 测绘通报, 2025, 0(2): 48-52,63.
[5]	秦晓琼, 张雅轩, 徐彬涛, 刘宇舟, 刘镇诚, 洪成雨, 陈湘生, 汪驰升. 联合时序InSAR和现场测量的地铁枢纽施工形变监测与多参量风险评估[J]. 测绘通报, 2025, 0(2): 71-76.
[6]	金霄, 王鹏, 葛礼呈, 王雨佳. DS-InSAR技术在北京大兴国际机场地表沉降监测中的应用[J]. 测绘通报, 2025, 0(12): 34-40.
[7]	王轶虹, 石一凡, 吴勇锋, 梁文广. 基于TS-InSAR技术的长江沿岸水闸沉降监测[J]. 测绘通报, 2025, 0(10): 119-126.
[8]	原辉, 胡帆, 范晶晶, 俞华, 王帅. 集成随机配置网络在输电线路覆冰预测中的应用[J]. 测绘通报, 2025, 0(1): 29-34.
[9]	黄标, 张辉, 尹剑辉. 基于时序InSAR技术的工业园区地表形变监测[J]. 测绘通报, 2024, 0(6): 157-163.
[10]	毕凌宇, 孙承志, 乔申. 基于SBAS-InSAR与MA-PSO-BP的南京河西地区地表沉降监测及预测分析[J]. 测绘通报, 2024, 0(4): 48-53,82.
[11]	俞文轩, 李益敏, 计培琨, 马恩华, 吕圣彬. 基于升降轨SAR数据的六库街道地表形变监测及地理探测机制[J]. 测绘通报, 2024, 0(12): 24-32.
[12]	王本浩, 王延霞, 项学泳, 胡洪. 结合DS-InSAR和LSTM的矿区地面沉降监测与预测[J]. 测绘通报, 2024, 0(11): 44-48.
[13]	乔申, 孙承志, 毕凌宇. 基于时序InSAR技术的南京市地铁沿线沉降监测分析[J]. 测绘通报, 2024, 0(10): 64-70.
[14]	张领旗, 谢酬, 陈蜜, 田帮森, 杨知, 朱玉. 时序InSAR技术在三峡库区特高压输电通道滑坡隐患识别的应用[J]. 测绘通报, 2023, 0(2): 97-103.
[15]	黄友菊, 覃怡婷, 吴慧, 韦强. 多时间基线集时序InSAR形变监测：以平寨水库为例[J]. 测绘通报, 2023, 0(11): 139-144.