联合机器学习与SBAS-InSAR的青藏高原冻土形变监测

doi:10.13474/j.cnki.11-2246.2025.0408

摘要/Abstract

摘要： 受全球气候变暖影响,青藏高原冻土退化和地表失稳问题不断加剧,对基础设施的建设维护和区域社会经济发展造成阻碍。近年来,SBAS-InSAR技术已在冻土地表形变监测中得到广泛应用,但由于青藏高原部分地区存在较为严重的失相干现象,导致形变监测结果出现空间不连续性,进而无法获得全面且精细的监测结果。针对上述问题,本文提出了一种联合机器学习与SBAS-InSAR的冻土形变监测方法,选取西藏阿里门士乡为研究区域,使用2020年1月7日至2021年6月6日共43景Sentinel-1A降轨影像数据提取地表形变信息;综合多类环境因子数据生成训练集后,引入机器学习模型拟合SBAS-InSAR监测结果与环境因子之间的内在关系,从而获取研究区连续形变速率图。结果表明,联合随机森林模型与SBAS-InSAR的方法效果最优,通过该方法对冻土形变缺失区域进行插值能极大提高原有SBAS-InSAR方法的监测覆盖率,其插值结果平均误差和均方根误差分别为0.459和0.739 mm/a。

关键词: SBAS-InSAR, 机器学习, 地表形变, 冻土, Sentinel-1A

Abstract: Affected by global climate change, the degradation of permafrost and surface instability in the Qinghai-Xizang Plateau have been continuously intensifying, posing obstacles to the construction and maintenance of infrastructure as well as regional socio-economic development. In recent years, SBAS-InSAR technology has been widely applied in monitoring surface deformation of permafrost. However, due to severe decorrelation phenomena in some areas of the Qinghai-Xizang Plateau, the deformation monitoring results exhibit spatial discontinuity, making it difficult to obtain comprehensive and detailed monitoring outcomes. To address these issues, this paper proposes a method for monitoring permafrost deformation that integrates machine learning with SBAS-InSAR. Taking the Menshi Township in Ali, Xizang, as the study area, a total of 43 descending Sentinel-1A images from January 7, 2020, to June 6, 2021, are used to extract surface deformation information. After generating a training dataset by integrating multiple environmental factor data, a machine learning model is introduced to fit the intrinsic relationship between SBAS-InSAR monitoring results and environmental factors, thereby obtaining a continuous deformation rate map of the study area. The results indicate that the method combining the random forest model with SBAS-InSAR performs optimally. By interpolating the missing regions of permafrost deformation using this method, the monitoring coverage of the original SBAS-InSAR method can be significantly improved, with an average error and root mean square error of 0.459 and 0.739 mm/a, respectively, for the interpolation results.

Key words: SBAS-InSAR, machine learning, surface deformation, frozen soil, Sentinel-1A

中图分类号:

P237

杨洋, 贾洪果, 柏铮航, 刘宇辰. 联合机器学习与SBAS-InSAR的青藏高原冻土形变监测[J]. 测绘通报, 2025, 0(4): 45-50.

YANG Yang, JIA Hongguo, BAI Zhenghang, LIU Yuchen. Integrated monitoring of permafrost deformation in the Qinghai-Xizang Plateau using machine learning and SBAS-InSAR[J]. Bulletin of Surveying and Mapping, 2025, 0(4): 45-50.

参考文献

[1] 徐学祖.冻土物理学[M].北京:科学出版社,2001.
[2] 施烨辉.列车荷载和冻融循环作用下冻土路基稳定性研究[D].北京:北京交通大学,2011.
[3] 多吉罗布.青藏公路多年冻土路基病害诊治技术研究[D].西安:长安大学,2002.
[4] 赵林.青藏高原多年冻土活动层的冻融过程以及季节冻土的变化[D].北京:中国科学院,2004.
[5] 洪兆阳,金双根.利用时序PS-InSAR监测青藏高原冻土区地表形变[J].测绘通报,2021(1):35-40.
[6] 李珊珊,李志伟,胡俊,等.SBAS-InSAR技术监测青藏高原季节性冻土形变[J].地球物理学报,2013,56(5):1476-1486.
[7] 李震,李新武,刘永智,等.差分干涉SAR冻土形变检测方法研究[J].冰川冻土,2004,26(4):389-396.
[8] XU Zhida,JIANG Liming,NIU Fujun,et al.Monitoring regional-scale surface deformation of the continuous permafrost in the Qinghai-Tibet Plateau with time-series InSAR analysis[J].Remote Sensing,2022,14(13):2987.
[9] 李振今,王志勇,叶凯乐,等.联合时间序列相干性和后向散射系数的黄河三角洲湿地分类[J].测绘通报,2023(2):52-57.
[10] SHENG Yifan,XU Guangli,JIN Bijing,et al.Data-driven landslide spatial prediction and deformation monitoring:a case study of Shiyan city,China[J].Remote Sensing,2023,15(21):5256.
[11] ZHAO Fumeng,GONG Wenping,REN Tianhe,et al.Permafrost stability mapping on the Tibetan Plateau by integrating time-series InSAR and the random forest method[J].Remote Sensing,2023,15(9):2294.
[12] ABEDINIA A,SEYDI V.Building semi-supervised decision trees with semi-cart algorithm[J].International Journal of Machine Learning and Cybernetics,2024,15(10):4493-4510.
[13] 冀建任,王竞雪,王丽芹.基于SVM混合核的不透水面提取及扩张分析[J].测绘通报,2024(3):43-48.
[14] 魏绍军,廖孟光,邱丙水.基于分布式光纤的地铁隧道安全风险监测技术及其应用[J].测绘通报,2024(6):164-170.
[15] ZHAO Lin,PING C L,YANG Daqing,et al.Changes of climate and seasonally frozen ground over the past 30 years in Qinghai-Xizang (Tibetan) Plateau,China[J].Global and Planetary Change,2004,43(1/2):19-31.
[16] RUSH M,RAJARAM H,ANDERSON R S,et al.Modeling aspect-controlled evolution of ground thermal regimes on montane hillslopes[J].Journal of Geophysical Research:Earth Surface,2021,126(8):e2021JF006126.
[17] ZHAO Rong,LI Zhiwei,FENG Guangcai,et al.Monitoring surface deformation over permafrost with an improved SBAS-InSAR algorithm:with emphasis on climatic factors modeling[J].Remote Sensing of Environment,2016,184:276-287.
[18] CHEN Jie,WU Tonghua,ZOU Defu,et al.Magnitudes and patterns of large-scale permafrost ground deformation revealed by Sentinel-1 InSAR on the central Qinghai-Tibet Plateau[J].Remote Sensing of Environment,2022,268:112778.
[19] 纪俊红,马铭阳,崔铁军,等.GSK-XGBoost模型在井底风温预测中的应用[J].中国安全生产科学技术,2022,18(3):131-136.
[20] CUI Kai,QIN Xiaotong.Landslide risk assessment of frozen soil slope in Qinghai Tibet Plateau during spring thawing period under the coupling effect of moisture and heat[J].Natural Hazards,2023,115(3):2399-2416.