广域滑坡灾害隐患InSAR显著性形变区深度学习识别技术

doi:10.11947/j.AGCS.2022.20220303

摘要/Abstract

摘要： 全面识别和发现地质灾害隐患,已成为我国地质灾害防治的重大实际需求。目前,基于InSAR技术和深度学习相结合用于广域尺度下地质灾害隐患智能识别应用效果与适用性还需要进一步探索与研究。本文基于Stacking InSAR技术获得地表形变相位数据,利用深度学习检测识别正在变形的滑坡隐患位置与分布,确定显著性形变区边界,探索将上述技术方法推广到一定的广域范围和动态更新数据集。结果显示,测试数据集显著性形变区平均识别精度为0.69,召回率为0.67,F₁ score为0.67,动态更新数据集识别精度为0.85,召回率为0.58,F₁ score为0.68。研究表明,本文方法在广域地灾隐患识别中具有应用可行性,可为地质灾害监测预警提供理论基础与技术支撑。

关键词: 地质灾害隐患, 显著性形变区, 深度学习

Abstract: Comprehensive identification and discovery of potential landslide hazards has become a major practical demand of geological hazard prevention and control in China. At present, the application effect and applicability of the combination of InSAR technology and deep learning for the intelligent identification of geological hazards at large scale are still worthy of further exploration and research, this paper obtained the phase data of surface deformation based on stacking interferometric synthetic aperture radar (Stacking InSAR) technology, used deep learning to identify the location and distribution of the deforming landslide hazards, and determined the boundary of the significant deformation zone of potential landslide hazards. The above technical methods were exploratively applied to test and dynamic update data sets. The average identification precision, recall and F₁ score value of the test data set were 0.69, 0.67 and 0.67, respectively. The identification precision, recall and F₁ score value of the dynamic update data set were 0.85, 0.58 and 0.68, respectively. The results showed that the technical method used in this paper is feasible in the identification of potential landslide hazards in a wide area, and can provide theory and technical support for geological disaster monitoring and early warning.

Key words: potential landslide hazard, significant deformation zone, deep learning

中图分类号:

P237

吴琼, 葛大庆, 于峻川, 张玲, 李曼, 刘斌, 王艳, 马燕妮, 刘宏娟. 广域滑坡灾害隐患InSAR显著性形变区深度学习识别技术[J]. 测绘学报, 2022, 51(10): 2046-2055.

WU Qiong, GE Daqing, YU Junchuan, ZHANG Ling, LI Man, LIU Bin, WANG Yan, MA Yanni, LIU Hongjuan. Deep learning identification technology of InSAR significant deformation zone of potential landslide hazard at large scale[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(10): 2046-2055.

参考文献

[1] 赵超英, 刘晓杰, 张勤, 等. 甘肃黑方台黄土滑坡InSAR识别、监测与失稳模式研究[J]. 武汉大学学报(信息科学版), 2019, 44(7): 996-1007. ZHAO Chaoying, LIU Xiaojie, ZHANG Qin, et al. Research on loess landslide identification, monitoring and failure mode with InSAR technique in Heifangtai, Gansu[J]. Geomatics and Information Science of Wuhan University, 2019, 44(7): 996-1007.
[2] LACROIX P, HANDWERGER A L, BIÈVRE G. Life and death of slow-moving landslides[J]. Nature Reviews Earth & Environment, 2020, 1(8): 404-419.
[3] 韩军强. 高精度GNSS实时滑坡变形监测技术及环境建模分析研究[J]. 测绘学报, 2020, 49(3): 397. DOI: 10.11947/j.AGCS.2020.20190177. HAN Junqiang. Research on high precision GNSS real time landslide deformation monitoring technology and environmental modeling[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(3): 397. DOI: 10.11947/j.AGCS.2020.20190177.
[4] 白正伟, 张勤, 黄观文, 等. “轻终端+行业云”的实时北斗滑坡监测技术[J]. 测绘学报, 2019, 48(11): 1424-1429. DOI: 10.11947/j.AGCS.2019.20190167. BAI Zhengwei, ZHANG Qin, HUANG Guanwen, et al. Real-time BeiDou landslide monitoring technology of “light terminal plus industry cloud”[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(11): 1424-1429. DOI: 10.11947/j.AGCS.2019.20190167.
[5] 朱建军, 李志伟, 胡俊. InSAR变形监测方法与研究进展[J]. 测绘学报, 2017, 46(10): 1717-1733. DOI: 10.11947/j.AGCS.2017.20170350. ZHU Jianjun, LI Zhiwei, HU Jun. Research progress and methods of InSAR for deformation monitoring[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10): 1717-1733. DOI: 10.11947/j.AGCS.2017.20170350.
[6] CARLÀ T, INTRIERI E, RASPINI F, et al. Perspectives on the prediction of catastrophic slope failures from satellite InSAR[J]. Scientific Reports, 2019, 9(1): 14137.
[7] 吴立新, 李佳, 苗则朗, 等. 冰川流域孕灾环境及灾害的天空地协同智能监测模式与方向[J]. 测绘学报, 2021, 50(8): 1109-1121. DOI: 10.11947/j.AGCS.2021.20210107. WU Lixin, LI Jia, MIAO Zelang, et al. Pattern and directions of spaceborne-airborne-ground collaborated intelligent monitoring on the geo-hazards developing environment and disasters in glacial basin[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8): 1109-1121. DOI: 10.11947/j.AGCS.2021.20210107.
[8] 许强. 对地质灾害隐患早期识别相关问题的认识与思考[J]. 武汉大学学报(信息科学版), 2020, 45(11): 1651-1659. XU Qiang. Understanding and consideration of related issues in early identification of potential geohazards[J]. Geomatics and Information Science of Wuhan University, 2020, 45(11): 1651-1659.
[9] 葛大庆, 戴可人, 郭兆成, 等. 重大地质灾害隐患早期识别中综合遥感应用的思考与建议[J]. 武汉大学学报(信息科学版), 2019, 44(7): 949-956. GE Daqing, DAI Keren, GUO Zhaocheng, et al. Early identification of serious geological hazards with integrated remote sensing technologies: thoughts and recommendations[J]. Geomatics and Information Science of Wuhan University, 2019, 44(7): 949-956.
[10] 朱庆, 曾浩炜, 丁雨淋, 等. 重大滑坡隐患分析方法综述[J]. 测绘学报, 2019, 48(12): 1551-1561. DOI: 10.11947/j.AGCS.2019.20190452. ZHU Qing, ZENG Haowei, DING Yulin, et al. A review of major potential landslide hazards analysis[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(12): 1551-1561. DOI: 10.11947/j.AGCS.2019.20190452.
[11] 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. ZHANG Lu, LIAO Mingsheng, DONG Jie, et al. Early detection of landslide hazards in mountainous areas of West China using times series SAR interferometry: a case study of Danba, Sichuan[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12): 2039-2049.
[12] 李晓恩, 周亮, 苏奋振, 等. InSAR技术在滑坡灾害中的应用研究进展[J]. 遥感学报, 2021, 25(2): 614-629. LI Xiaoen, ZHOU Liang, SU Fenzhen, et al. Application of InSAR technology in landslide hazard: progress and prospects[J]. Journal of Remote Sensing, 2021, 25(2): 614-629.
[13] BARRA A, SOLARI L, BÉJAR-PIZARRO M, et al. A methodology to detect and update active deformation areas based on Sentinel-1 SAR images[J]. Remote Sensing, 2017, 9(10): 1002.
[14] SHI Xuguo, YANG Chao, ZHANG Lu, et al. Mapping and characterizing displacements of active loess slopes along the upstream Yellow River with multi-temporal InSAR datasets[J]. Science of the Total Environment, 2019, 674: 200-210.
[15] BIANCHINI S, CIGNA F, RIGHINI G, et al. Landslide hotspot mapping by means of persistent scatterer interferometry[J]. Environmental Earth Sciences, 2012, 67(4): 1155-1172.
[16] CALÒ F, ARDIZZONE F, CASTALDO R, et al. Enhanced landslide investigations through advanced DInSAR techniques: the Ivancich case study, Assisi, Italy[J]. Remote Sensing of Environment, 2014, 142: 69-82.
[17] TOMÁS R, PAGÁN J I, NAVARRO J A, et al. Semi-automatic identification and pre-screening of geological-geotechnical deformational processes using persistent scatterer interferometry datasets[J]. Remote Sensing, 2019, 11(14): 1675.
[18] DING Anzi, ZHANG Qingyong, ZHOU Xinmin, et al. Automatic recognition of landslide based on CNN and texture change detection[C]//Proceedings of the 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC). Wuhan: IEEE, 2016: 444-448.
[19] YU Hong, MA Yi, WANG Longfei, et al. A landslide intelligent detection method based on CNN and RSG_R[C]//Proceedings of 2017 IEEE International Conference on Mechatronics and Automation (ICMA). Takamatsu, Japan: IEEE, 2017: 40-44.
[20] GHORBANZADEH O, BLASCHKE T, GHOLAMNIA K, et al. Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection[J]. Remote Sensing, 2019, 11(2): 196.
[21] JI Shuping, YU Dawen, SHEN Chaoyong, et al. Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks[J]. Landslides, 2020, 17(6): 1337-1352.
[22] QIN Shengwu, GUO Xu, SUN Jingbo, et al. Landslide detection from open satellite imagery using distant domain transfer learning[J]. Remote Sensing, 2021, 13(17): 3383.
[23] SANDWELL D T, PRICE E J. Phase gradient approach to stacking interferograms[J]. Journal of Geophysical Research: Solid Earth, 1998, 103(B12): 30183-30204.
[24] 沙永莲, 刘国祥, 王晓文, 等. 基于Stacking时序InSAR的北泉矿区沉陷监测[J]. 测绘科学技术, 2020, 8(2): 60-67. SHA Yonglian, LIU Guoxiang, WANG Xiaowen, et al. Ground subsidence detection of Beiquan mining area based on Stacking time-series InSAR[J]. InSAR Geomatics Science and Technology, 2020, 8(2): 60-67.
[25] 王庆. 基于深度学习的遥感影像变化检测方法研究[D]. 武汉: 武汉大学, 2019. WANG Qing. Research on remote sensing imagery change detection method based on deep learning[D]. Wuhan: Wuhan University, 2019.
[26] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, SO, USA: IEEE, 2014: 580-587.
[27] GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015: 1440-1448.
[28] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(6): 1137-1149.
[29] HE Kaiming, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017.
[30] YU Bo, CHEN Fang, XU Chong. Landslide detection based on contour-based deep learning framework in case of national scale of Nepal in 2015[J]. Computers & Geosciences, 2020, 135: 104388.
[31] 刘斌, 葛大庆, 王珊珊, 等. TOPS和ScanSAR模式InSAR在广域地灾隐患识别中的联合应用[J]. 武汉大学学报(信息科学版), 2020, 45(11): 109-115. LIU Bin, GE Daqing, WANG Shanshan, et al. Combining application of TOPS and ScanSAR InSAR in large-scale geohazards identification[J]. Geomatics and Information Science of Wuhan University, 2020, 45(11): 1756-1762.