测绘通报 ›› 2026, Vol. 0 ›› Issue (10): 105-111,126.doi: 10.13474/j.cnki.11-2246.2026.1016

• 学术研究 • 上一篇    

融合GNSS和InSAR数据的新近吹填场地沉降监测预测

肖时辉1, 王创1,2, 邱芬明2, 谷任国3, 樊天慧3, 程博伟4, 肖柯良4, 束云龙5   

  1. 1. 珠海大横琴股份有限公司, 广东 珠海 519000;
    2. 珠海大横琴城投建设有限公司, 广东 珠海 519000;
    3. 华南理工大学土木与交通学院, 广东 广州 510000;
    4. 金属矿山安全开采与灾害防治全国重点实验室, 安徽 马鞍山 243000;
    5. 南华大学资源环境与安全工程学院, 湖南 衡阳 421001
  • 收稿日期:2025-12-01 发布日期:2026-11-06
  • 通讯作者: 谷任国。E-mail:rggu@scut.edu.cn
  • 作者简介:肖时辉(1973—),男,硕士,教授级高级工程师,研究方向为隧道与地下工程。E-mail:xsh7179@163.com
  • 基金资助:
    国家自然科学基金重大仪器专项(41827807)

Subsidence monitoring and prediction for recently reclaimed sites integrating GNSS and InSAR data

Xiao Shihui1, Wang Chuang1,2, Qiu Fenming2, Gu Renguo3, Fan Tianhui3, Cheng Bowei4, Xiao Keliang4, Shu Yunlong5   

  1. 1. Zhuhai Da Hengqin Co., Ltd., Zhuhai 519000, China;
    2. Zhuhai Da Hengqin City Investment Construction Co., Ltd., Zhuhai 519000, China;
    3. School of Civil Engineering and Transportation, South China University of Technology, Guangzhou 510000, China;
    4. State Key Laboratory of Metal Mine Mining Safety and Disaster Prevention and Control, Maanshan 243000, China;
    5. School of Resources Environment and Safety Engineering, University of South China, Hengyang 421001, China
  • Received:2025-12-01 Published:2026-11-06

摘要: [目的] 针对新近吹填场地地表形变监测中,单一测量手段在空间覆盖与精度稳定性方面不足的问题,本文提出了一种融合GNSS与InSAR数据并结合深度学习的沉降监测与预测方法。[方法] 首先,以珠海市斗门区人工吹填场地为研究区,利用SBAS-InSAR技术处理2022年7月至2024年2月共22景Sentinel-1A影像,获取沉降时序与空间分布;然后,采用卡尔曼滤波实现GNSS与InSAR观测的融合,获得更稳定的形变序列;最后,构建基于Adam优化器的LSTM模型开展沉降预测,并采用MAE、RMSE与R2对预测效果进行评价。[结果] 结果表明:研究区沉降具有显著空间差异;融合后3个GNSS监测点形变序列标准差分别由 4.939 77、2.276 89、2.660 43 mm降至3.863 44、2.000 49、2.298 29 mm;与仅基于InSAR数据的预测相比,融合数据的预测误差分别降低11.27%、13.61%和12.38%。[结论] 研究表明,本文方法可有效提升吹填场地沉降序列的稳定性与预测精度,为沿海工程建设区沉降监测与风险预警提供技术支撑。

关键词: SBAS-InSAR, GNSS, 卡尔曼滤波, Adam-LSTM, 沉降预测

Abstract: [Purposes] To address the limitations of single monitoring techniques in terms of spatial coverage and stability for surface deformation monitoring of recently dredged and filled sites,a subsidence monitoring and prediction approach integrating GNSS and InSAR data with deep learning is proposed. [Methods] Taking an artificial reclaimed area in Doumen district,Zhuhai city,as the study area,the SBAS-InSAR technique was first applied to 22 Sentinel-1A images acquired from July 2022 to February 2024 to obtain subsidence time series and spatial distribution characteristics.Subsequently,a Kalman filter was employed to fuse GNSS and InSAR observations,generating deformation time series with improved stability.On this basis,a long short-term memory(LSTM)network optimized using the Adam algorithm was constructed for subsidence prediction,and the model performance was evaluated using MAE,RMSE,and R2. [Findings] The results indicate that subsidence in the study area exhibits significant spatial heterogeneity.After data fusion,the standard deviations of deformation time series at three GNSS monitoring points decreased from 4.939 77, 2.276 89,and 2.660 43 mm to 3.863 44,2.000 49,and 2.298 29 mm,respectively.Compared with predictions based solely on InSAR data,the prediction errors using the fused data were reduced by 11.27%,13.61%,and 12.38%. [Conclusions] The proposed method effectively improves the stability of subsidence time series and the accuracy of subsidence prediction,providing technical support for subsidence monitoring and risk warning in coastal engineering areas.

Key words: SBAS-InSAR, GNSS, Kalman filtering, Adam-LSTM, subsidence prediction

中图分类号: