浏览全部资源
扫码关注微信
Received：28 August 2025，
Published：07 April 2026
移动端阅览
白鹤滩水电站作为国家重大工程，其库区地质条件复杂，蓄水后岸坡稳定性监测至关重要。传统InSAR技术依赖形变速率指标，难以揭示时序演变规律的问题，本文融合迁移学习与时间卷积网络（TCN），构建了一种时序形变模式智能识别模型，旨在提升库区形变演化特征的认知。研究利用2021年4月至2024年3月的Sentinel-1卫星数据，采用SBAS-InSAR技术反演获取整个库区的时序形变场，提出了一种“迁移学习增强的深度学习时序分类架构”：利用模拟样本数据进行预训练，再通过真实样本数据进行微调，研究建立了一个包含平稳、线性、阶跃、分段线性、幂次及未定义类的六维形变分类体系，并应用于白鹤滩库区的形变模式识别。结果表明：（1）库区97377个形变点分类统计显示：平稳型（45.6%）、分段线性型（24.4%）为主导模式，平稳型与低速率、高相干性显著相关；（2）石门坎滑坡受库水位滞时调控，抬升滞后蓄水峰值约2个月，野猪塘坡体呈现降雨触发的阶跃形变及水位—降水耦合的分段线性响应。本文突破了传统基于速率的单一分析框架，验证了迁移学习在降低时序标注成本方面的有效性，并表明多维形变模式解析能够为库区灾害风险的动态评估提供新的方法范式。
The Baihetan Hydropower Station
as a national mega-project
is located in a geologically complex reservoir area where slope stability monitoring after impoundment is crucial. Traditional InSAR techniques mainly rely on deformation rate indicators and thus face limitations in capturing the full temporal evolution of slope deformation. This study aims to overcome these limitations by developing an intelligent framework for time-series deformation pattern recognition to improve hazard identification and risk assessment in the reservoir area.
Sentinel-1 SAR data spanning April 2021 to March 2024 were processed using the SBAS-InSAR technique to retrieve the reservoir-wide deformation field. A transfer learning-enhanced deep learning architecture was proposed
in which synthetic samples were used for pretraining and real samples for fine-tuning. Based on this framework
a six-class taxonomy of deformation patterns—stable
linear
step-like
piecewise linear
power-law
and undefined—was established. A Temporal Convolutional Network (TCN) was then applied to classify deformation modes across the Baihetan reservoir.
(1) Among 97377 deformation points
the dominant patterns were stable (45.6%) and piecewise linear (24.4%)
with stable deformation strongly associated with low velocity and high coherence. (2) The Shimenkan landslide exhibited a delayed uplift response regulated by reservoir water level
lagging peak impoundment by about two months.(3) The Yezhutang slope showed rainfall-triggered step-like deformation and a piecewise linear response under coupled water level-precipitation forcing.
The findings demonstrate that transfer learning effectively reduces labeling costs
while multidimensional deformation pattern analysis provides a new paradigm for dynamic risk assessment of reservoir-induced geohazards.
Aguiar P , Cunha A , Bakon M , Ruiz-Armenteros A M and Sousa J J . 2021 . Multivariate outlier detection in postprocessing of multi-temporal PS-InSAR results using deep learning . Procedia Computer Science , 181 : 1146 - 1153 [ DOI: 10.1016/j.procs.2021.01.326 http://dx.doi.org/10.1016/j.procs.2021.01.326 ]
Bai S J , Kolter J Z and Koltun V . 2018 . An empirical evaluation of generic convolutional and recurrent networks for sequence modeling . arXiv preprint arXiv : 1803 . 01271 [ DOI: 10.48550/arXiv.1803.01271 http://dx.doi.org/10.48550/arXiv.1803.01271 ]
Berardino P , Fornaro G , Lanari R and Sansosti E . 2002 . A new algorithm for surface deformation monitoring based on small baseline differential SAR interferograms . IEEE Transactions on Geoscience and Remote Sensing , 40 ( 11 ): 2375 - 2383 [ DOI: 10.1109/TGRS.2002.803792 http://dx.doi.org/10.1109/TGRS.2002.803792 ]
Berti M , Corsini A , Franceschini S and Iannacone J P . 2013 . Automated classification of Persistent Scatterers Interferometry time series . Natural Hazards and Earth System Sciences , 13 ( 8 ): 1945 - 1958 [ DOI: 10.5194/nhess-13-1945-2013 http://dx.doi.org/10.5194/nhess-13-1945-2013 ]
Cai J H , Zhang L , Dong J , Guo J C , Wang Y A and Liao M S . 2023 . Automatic identification of active landslides over wide areas from time-series InSAR measurements using Faster RCNN . International Journal of Applied Earth Observation and Geoinformation , 124 : 103516 [ DOI: 10.1016/j.jag.2023.103516 http://dx.doi.org/10.1016/j.jag.2023.103516 ]
Dai F C and Deng J H . 2020 . Development characteristics of landslide hazards in Three-Rivers Basin of southeast Tibetan Plateau . Advanced Engineering Sciences , 52 ( 5 ): 3 - 15
戴福初 , 邓建辉 . 2020 . 青藏高原东南三江流域滑坡灾害发育特征 . 工程科学与技术 , 52 ( 5 ): 3 - 15 [ DOI: 10.15961/j.jsuese.202000651 http://dx.doi.org/10.15961/j.jsuese.202000651 ]
Dai K R , Chen C , Shi X L , Wu M T , Feng W K , Xu Q , Liang R B , Zhuo G C and Li Z H . 2023 . Dynamic landslides susceptibility evaluation in Baihetan Dam area during extensive impoundment by integrating geological model and InSAR observations . International Journal of Applied Earth Observation and Geoinformation , 116 : 103157 [ DOI: 10.1016/j.jag.2022.103157 http://dx.doi.org/10.1016/j.jag.2022.103157 ]
Dun J , Feng W K , Yi X Y , Ding Z W , Zhuo G C , Dai K R and Wu M T . 2025 . Detection and updation of landslide inventory before and during impoundment in the Baihetan reservoir area using multi-temporal InSAR datasets . Scientific Reports , 15 ( 1 ): 9889 [ DOI: 10.1038/s41598-025-94520-1 http://dx.doi.org/10.1038/s41598-025-94520-1 ]
Dun J W , Feng W K , Yi X Y , Zhang G Q and Wu M T . 2023 . Early InSAR identification of active landslide before impoundment in baihetan reservoir area—A case study of Hulukou town xiangbiling section . Journal of Engineering Geology , 31 ( 2 ): 479 - 492
顿佳伟 , 冯文凯 , 易小宇 , 张国强 , 吴明堂 . 2023 . 白鹤滩库区蓄水前活动性滑坡InSAR早期识别研究——以葫芦口镇至象鼻岭段为例 . 工程地质学报 , 31 ( 2 ): 479 - 492 [ DOI: 10.13544/j.cnki.jeg.2022-0016 http://dx.doi.org/10.13544/j.cnki.jeg.2022-0016 ]
Festa D , Bonano M , Casagli N , Confuorto P , De Luca C , Del Soldato M , Lanari R , Lu P , Manunta M , Manzo M , Onorato G , Raspini F , Zinno I and Casu F . 2022 . Nation-wide mapping and classification of ground deformation phenomena through the spatial clustering of P-SBAS InSAR measurements: Italy case study . ISPRS Journal of Photogrammetry and Remote Sensing , 189 : 1 - 22 [ DOI: 10.1016/j.isprsjprs.2022.04.022 http://dx.doi.org/10.1016/j.isprsjprs.2022.04.022 ]
Festa D , Novellino A , Hussain E , Bateson L , Casagli N , Confuorto P , Del Soldato M and Raspini F . 2023 . Unsupervised detection of InSAR time series patterns based on PCA and K-means clustering . International Journal of Applied Earth Observation and Geoinformation , 118 : 103276 [ DOI: 10.1016/j.jag.2023.103276 http://dx.doi.org/10.1016/j.jag.2023.103276 ]
Gagliardi V , Tosti F , Ciampoli L B , D'Amico F , Alani A M , Battagliere M L and Benedetto A . 2021 . Monitoring of bridges by MT-InSAR and unsupervised machine learning clustering techniques // Proceedings Volume 11863 , Earth Resources and Environmental Remote Sensing/GIS Applications XII. Online : SPIE: 132 - 140 [ DOI: 10.1117/12.2597509 http://dx.doi.org/10.1117/12.2597509 ]
He K M , Zhang X Y , Ren S Q and Sun J . 2016 . Deep residual learning for image recognition // Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas : IEEE: 770 - 778 [ DOI: 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ]
He Y D and Zhao J B . 2019 . Temporal convolutional networks for anomaly detection in time series . Journal of Physics: Conference Series , 1213 ( 4 ): 042050 [ DOI: 10.1088/1742-6596/1213/4/042050 http://dx.doi.org/10.1088/1742-6596/1213/4/042050 ]
Hinton G E and Salakhutdinov R R . 2006 . Reducing the dimensionality of data with neural networks . Science , 313 ( 5786 ): 504 - 507 [ DOI: 10.1126/science.1127647 http://dx.doi.org/10.1126/science.1127647 ]
Ketelaar V B H . 2009 . Satellite Radar Interferometry: Subsidence Monitoring Techniques . Dordrecht : Springer [ DOI: 10.1007/978-1-4020-9428-6 http://dx.doi.org/10.1007/978-1-4020-9428-6 ]
Kulshrestha A , Chang L and Stein A . 2022 . Use of LSTM for sinkhole-related anomaly detection and classification of InSAR deformation time series . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 15 : 4559 - 4570 [ DOI: 10.1109/JSTARS.2022.3180994 http://dx.doi.org/10.1109/JSTARS.2022.3180994 ]
Lanari R , Berardino P , Bonano M , Casu F , Manconi A , Manunta M , Manzo M , Pepe A , Pepe S , Sansosti E , Solaro G , Tizzani P and Zeni G . 2010 . Surface displacements associated with the L'Aquila 2009 Mw 6.3 earthquake (central Italy): new evidence from SBAS‐DInSAR time series analysis . Geophysical Research Letters , 37 ( 20 ): L 20309 [ DOI: 10.1029/2010GL044780 http://dx.doi.org/10.1029/2010GL044780 ]
Lattari F , Rucci A and Matteucci M . 2022 . A deep learning approach for change points detection in InSAR time series . IEEE Transactions on Geoscience and Remote Sensing , 60 : 5223916 [ DOI: 10.1109/tgrs.2022.3155969 http://dx.doi.org/10.1109/tgrs.2022.3155969 ]
Li M H , Wu H F , Yang M S , Huang C and Tang B H . 2023 . Trend classification of InSAR displacement time series using SAE–CNN . Remote Sensing , 16 ( 1 ): 54 [ DOI: 10.3390/rs16010054 http://dx.doi.org/10.3390/rs16010054 ]
Li M H , Zhang L , Shi X G , Liao M S and Yang M S . 2019 . Monitoring active motion of the Guobu landslide near the Laxiwa Hydropower Station in China by time-series point-like targets offset tracking . Remote Sensing of Environment , 221 : 80 - 93 [ DOI: 10.1016/j.rse.2018.11.006 http://dx.doi.org/10.1016/j.rse.2018.11.006 ]
Li Y C and Ke Y H . 2015 . Spatial-temporal heterogeneity of land subsidence evolution in Beijing based on InSAR and cluster analysis // IET International Radar Conference 2015 . Hangzhou : IET: 1 - 5 [ DOI: 10.1049/cp.2015.1423 http://dx.doi.org/10.1049/cp.2015.1423 ]
Mirmazloumi S M , Gambin A F , Palamà R , Crosetto M , Wassie Y , Navarro J A , Barra A and Monserrat O . 2022a . Supervised machine learning algorithms for ground motion time series classification from InSAR data . Remote Sensing , 14 ( 15 ): 3821 [ DOI: 10.3390/rs14153821 http://dx.doi.org/10.3390/rs14153821 ]
Mirmazloumi S M , Wassie Y , Navarro J A , Palamà R , Krishnakumar V , Barra A , Cuevas-González M , Crosetto M and Monserrat O . 2022b . Classification of ground deformation using Sentinel-1 persistent scatterer interferometry time series . GIScience and Remote Sensing , 59 ( 1 ): 374 - 392 [ DOI: 10.1080/15481603.2022.2030535 http://dx.doi.org/10.1080/15481603.2022.2030535 ]
Montgomery D R , Sullivan K and Greenberg H M . 1998 . Regional test of a model for shallow landsliding . Hydrological Processes , 12 ( 6 ): 943 - 955 [ DOI: 10.1002/(SICI)1099-1085(199805)12:6<943::AID-HYP664>3.0.CO;2-Z http://dx.doi.org/10.1002/(SICI)1099-1085(199805)12:6<943::AID-HYP664>3.0.CO;2-Z ]
Salimans T and Kingma D P . 2016 . Weight normalization: a simple reparameterization to accelerate training of deep neural networks // Proceedings of the 30th International Conference on Neural Information Processing Systems . Barcelona : Curran Associates Inc.: 901 - 909
Savage J C , Svarc J L and Prescott W H . 2003 . Near‐field postseismic deformation associated with the 1992 Landers and 1999 Hector Mine, California, earthquakes . Journal of Geophysical Research: Solid Earth , 108 ( B9 ): 2432 [ DOI: 10.1029/2002jb002330 http://dx.doi.org/10.1029/2002jb002330 ]
Savitzky A and Golay M J E . 1964 . Smoothing and differentiation of data by simplified least squares procedures . Analytical Chemistry , 36 ( 8 ): 1627 - 1639 [ DOI: 10.1021/ac60214a047 http://dx.doi.org/10.1021/ac60214a047 ]
Schlögl M , Widhalm B and Avian M . 2021 . Comprehensive time-series analysis of bridge deformation using differential satellite radar interferometry based on Sentinel-1 . ISPRS Journal of Photogrammetry and Remote Sensing , 172 : 132 - 146 [ DOI: 10.1016/j.isprsjprs.2020.12.001 http://dx.doi.org/10.1016/j.isprsjprs.2020.12.001 ]
Schneider P J and Soergel U . 2021 . Clustering persistent scatterer points based on a hybrid distance metric // 43rd DAGM German Conference on Pattern Recognition . Bonn : Springer: 621 - 632 [ DOI: 10.1007/978-3-030-92659-5_40 http://dx.doi.org/10.1007/978-3-030-92659-5_40 ]
Shi X G , Hu X , Sitar N , Kayen R , Qi S W , Jiang H J , Wang X D and Zhang L . 2021 . Hydrological control shift from river level to rainfall in the reactivated Guobu slope besides the Laxiwa hydropower station in China . Remote Sensing of Environment , 265 : 112664 [ DOI: 10.1016/j.rse.2021.112664 http://dx.doi.org/10.1016/j.rse.2021.112664 ]
Tan T Y . 2022 . Early Identification and Monitoring of Reservoir Landslides based on InSAR Technology-Taking Baihe Tan Reservoir Area as an Example . Qinhuangdao : Yanshan University
谭天宇 . 2022 . 基于InSAR技术的库区滑坡早期识别与监测——以白鹤滩库区为例 . 秦皇岛 : 燕山大学 [ DOI: 10.27440/d.cnki.gysdu.2022.001980 http://dx.doi.org/10.27440/d.cnki.gysdu.2022.001980 ]
Tiwari A and Shirzaei M . 2024 . A novel machine learning and deep learning semi-supervised approach for automatic detection of InSAR-based deformation hotspots . International Journal of Applied Earth Observation and Geoinformation , 126 : 103611 [ DOI: 10.1016/j.jag.2023.103611 http://dx.doi.org/10.1016/j.jag.2023.103611 ]
Van Den Oord A , Dieleman S , Zen H , Simonyan K , Vinyals O , Graves A , Kalchbrenner N , Senior A and Kavukcuoglu K . 2016 . WaveNet: a generative model for raw audio . arXiv preprint arXiv : 1609 . 03499 [ DOI: 10.48550/arXiv.1609.03499 http://dx.doi.org/10.48550/arXiv.1609.03499 ]
Wang L Y , Deng K Z and Zheng M N . 2020 . Research on ground deformation monitoring method in mining areas using the probability integral model fusion D-InSAR, sub-band InSAR and offset-tracking . International Journal of Applied Earth Observation and Geoinformation , 85 : 101981 [ DOI: 10.1016/j.jag.2019.101981 http://dx.doi.org/10.1016/j.jag.2019.101981 ]
Wang Z L , Liao M S , Zhang L , Luo H and Dong J . 2019 . Detecting and characterizing deformations of the left bank slope near the Jinping hydropower station with time series Sentinel-1 data . Remote Sensing for Land and Resources , 31 ( 2 ): 204 - 209
王振林 , 廖明生 , 张路 , 罗恒 , 董杰 . 2019 . 基于时序Sentinel-1数据的锦屏水电站左岸边坡形变探测与特征分析 . 国土资源遥感 , 31 ( 2 ): 204 - 209 [ DOI: 10.6046/gtzyyg.2019.02.28 http://dx.doi.org/10.6046/gtzyyg.2019.02.28 ]
Wang Z Y , Xu J H , Shi X G , Wang J N , Zhang W and Zhang B . 2022 . Landslide inventory in the downstream of the Niulanjiang River with ALOS PALSAR and Sentinel-1 datasets . Remote Sensing , 14 ( 12 ): 2873 [ DOI: 10.3390/rs14122873 http://dx.doi.org/10.3390/rs14122873 ]
Wu H F , Feng B , Li M H , Yang M S , Zhang Z and Tang B H . 2025 . Self-supervised contrastive learning clustering method for InSAR time series deformation data . Journal of Remote Sensing (in Chinese) , 29 ( 7 ): 2442 - 2456
吴晗飞 , 俸彬 , 李梦华 , 杨梦诗 , 张震 , 唐伯惠 . 2025 . InSAR时序形变数据的自监督对比学习聚类方法 . 遥感学报 , 29 ( 7 ): 2442 - 2456 [ DOI: 10.11834/jrs.20254393 http://dx.doi.org/10.11834/jrs.20254393 ]
Wu M T , Fang Y F , Zhuo G C , Yi X Y , Dai K R , Chen J Q and Feng W K . 2023 . Comprehensive remote sensing identification of potential geohazards in Sanjiacun Reservoir Bank of Baihetan . Journal of Kunming University of Science and Technology (Natural Science) , 48 ( 3 ): 53 - 61
吴明堂 , 房云峰 , 卓冠晨 , 易小宇 , 戴可人 , 陈建强 , 冯文凯 . 2023 . 白鹤滩库区三家村库岸地质灾害隐患综合遥感识别 . 昆明理工大学学报(自然科学版) , 48 ( 3 ): 53 - 61 [ DOI: 10.16112/j.cnki.53-1223/n.2023.03.122 http://dx.doi.org/10.16112/j.cnki.53-1223/n.2023.03.122 ]
Xie M W , Huang J H , Wang Z F and Liu X Y . 2012 . Study on monitoring of rock and soil change in a large area . Science of Soil and Water Conservation , 10 ( 1 ): 59 - 64
谢谟文 , 黄洁慧 , 王增幅 , 刘翔宇 . 2012 . 广域岩土体变化监测研究 . 中国水土保持科学 , 10 ( 1 ): 59 - 64 [ DOI: 10.3969/j.issn.1672-3007.2012.01.010 http://dx.doi.org/10.3969/j.issn.1672-3007.2012.01.010 ]
Yang M S , Li M H , Huang C , Zhang R S and Liu R . 2024 . Exploring the InSAR deformation series using unsupervised learning in a built environment . Remote Sensing , 16 ( 8 ): 1375 [ DOI: 10.3390/rs16081375 http://dx.doi.org/10.3390/rs16081375 ]
Yang M S , Li S W and Yu H . 2025 . A transfer learning approach for deformation pattern recognition in InSAR time series . IEEE Transactions on Geoscience and Remote Sensing , 63 : 5205616 [ DOI: 10.1109/TGRS.2025.3543580 http://dx.doi.org/10.1109/TGRS.2025.3543580 ]
Yang Z R , Xi W F , Yang Z Q , Shi Z T , Huang G C , Guo J Q and Yang D Q . 2023 . Time-Lag response of landslide to reservoir water level fluctuations during the storage period: a case study of Baihetan reservoir . Water , 15 ( 15 ): 2732 [ DOI: 10.3390/w15152732 http://dx.doi.org/10.3390/w15152732 ]
Zhang D X , Wang G H , Yang T J , Zhang M C , Chen S H and Zhang F Y . 2013 . Satellite remote sensing-based detection of the deformation of a reservoir bank slope in Laxiwa Hydropower Station, China . Landslides , 10 ( 2 ): 231 - 238 [ DOI: 10.1007/s10346-012-0378-9 http://dx.doi.org/10.1007/s10346-012-0378-9 ]
Zhang R , Zhao X , Dong X J , Dai K R , Deng J , Zhuo G C , Yu B , Wu T T and Xiang J M . 2024 . Potential landslide identification in baihetan reservoir area based on C-/L-band synthetic aperture radar data and applicability analysis . Remote Sensing , 16 ( 9 ): 1591 [ DOI: 10.3390/rs16091591 http://dx.doi.org/10.3390/rs16091591 ]
Zhou Z K . 2023 . Study on the Deformation Failure Law, Development Mechanism and Stability of Bank Slope at the Initial Stage of Impoundment of Baihetan Reservoir in Jinsha River . Beijing : China University of Geosciences (Beijing) (周振凯 . 2023. 金沙江白鹤滩水库蓄水初期岸坡变形破坏规律、机制与稳定性研究 . 北京: 中国地质大学(北京)) [ DOI: 10.27493/d.cnki.gzdzy.2023.000066 http://dx.doi.org/10.27493/d.cnki.gzdzy.2023.000066 ]
相关文章
相关作者
相关机构
京公网安备11010802024621
