InSAR time-series deformation forecasting surrounding Salt Lake using deep transformer models

被引:21
|
作者
Wang, Jing [1 ]
Li, Chao [1 ]
Li, Lu [1 ]
Huang, Zhihua [1 ]
Wang, Chao [2 ,3 ,4 ]
Zhang, Hong [2 ,3 ,4 ]
Zhang, Zhengjia [5 ]
机构
[1] Zhejiang Lab, Res Inst Intelligent Comp, Hangzhou 311121, Peoples R China
[2] Chinese Acad Sci, Aerosp Informat Res Inst, Key Lab Digital Earth Sci, 9 Dengzhuang South Rd, Beijing 100094, Peoples R China
[3] Int Res Ctr Big Data Sustainable Dev Goals, Beijing 100094, Peoples R China
[4] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[5] China Univ Geosci, Fac Informat Engn, 388 Lumo Rd, Wuhan 430074, Peoples R China
基金
中国博士后科学基金;
关键词
InSAR; Qinghai -Tibet Plateau; Deformation prediction; Transformer; Salt Lake; Permafrost; TIBETAN PLATEAU; LAND SUBSIDENCE; SENTINEL-1; PREDICTION; INTERFEROMETRY; ALGORITHM; NETWORKS; OUTBURST; LEVEL;
D O I
10.1016/j.scitotenv.2022.159744
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The free and open data policy of Sentinel-1 SAR images enables Radar interferometry (InSAR) to perform time series surface deformation monitoring over large areas. InSAR deformation monitoring and prediction can investigate the freeze-thaw cycles of permafrost on the Qinghai-Tibet Plateau. However, the convolutional and recurrent neural net-works cannot accurately model long-term and complex relations in multivariate time series data, it is challenging to implement time series deformation prediction with high spatial resolution. In this paper, an innovative InSAR defor-mation prediction integrated algorithm based on the transformer models is proposed to predict time series deforma-tion more accurately surrounding Salt Lake. Compared with the other solutions, the unique feature of the proposed method is that: 1) this method takes advantage of the self-attention mechanism to study complicated dynamic defor-mation features of permafrost caused by temperature and other variables from InSAR time series deformation. 2) The transformer-based model can more accurately simulate seasonal and non-seasonal deformation signals, and is effective for short-term prediction of surface deformation in permafrost areas. The InSAR deformation prediction results dem-onstrate that the InSAR deformation prediction method achieves better prediction performance in predicting the de-formation trends of permafrost with a point scale compared with the prediction results of other models. Based on the predicted deformation and the water extraction results, the expansion trends surrounding Salt Lake are discussed and evaluated. The total area of Salt Lake increased by 57.32 km2 during the period 2015-2019. And Salt Lake maintained slowing expansion trend from 2019 to 2022. The time series deformation forecasting method can be used as a generic framework for modeling nonlinear deformation processes in complex permafrost areas, and it reveals the potential impact of the Salt Lake outburst event on the deformation processes and the degradation of permafrost.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Prediction of InSAR time-series deformation using deep convolutional neural networks
    Ma, Peifeng
    Zhang, Fan
    Lin, Hui
    REMOTE SENSING LETTERS, 2020, 11 (02) : 137 - 145
  • [2] PREDICTION OF INSAR URBAN SURFACE TIME-SERIES DEFORMATION USING DEEP NEURAL NETWORKS
    Liu, Yuhang
    Chen, Tao
    Li, Jun
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 5206 - 5209
  • [3] Prediction of InSAR deformation time-series using improved LSTM deep learning model
    Soni, Rupika
    Alam, Mohammad Soyeb
    Vishwakarma, Gajendra K.
    SCIENTIFIC REPORTS, 2025, 15 (01):
  • [4] Time-series forecasting of mortality rates using transformer
    Wang, Jun
    Wen, Lihong
    Xiao, Lu
    Wang, Chaojie
    SCANDINAVIAN ACTUARIAL JOURNAL, 2024, 2024 (02) : 109 - 123
  • [5] Deformation Monitoring of Reservoirs and Dams Using Time-Series InSAR
    Xiao R.
    He X.
    Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University, 2019, 44 (09): : 1334 - 1341
  • [6] Time-Series Prediction Approaches to Forecasting Deformation in Sentinel-1 InSAR Data
    Hill, P.
    Biggs, J.
    Ponce-Lopez, V.
    Bull, D.
    JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH, 2021, 126 (03)
  • [7] Ensemble Deep Learning Models for Forecasting Cryptocurrency Time-Series
    Livieris, Ioannis E.
    Pintelas, Emmanuel
    Stavroyiannis, Stavros
    Pintelas, Panagiotis
    ALGORITHMS, 2020, 13 (05)
  • [8] AN INTRODUCTION TO FORECASTING WITH TIME-SERIES MODELS
    BELL, WR
    INSURANCE MATHEMATICS & ECONOMICS, 1984, 3 (04): : 241 - 255
  • [9] FORECASTING GROWTH WITH TIME-SERIES MODELS
    PENA, D
    JOURNAL OF FORECASTING, 1995, 14 (02) : 97 - 105
  • [10] Scaling Deep Learning Models for Large Spatial Time-Series Forecasting
    Abbas, Zainab
    Ivarsson, Jon Reginbald
    Al-Shishtawy, Ahmad
    Vlassov, Vladimir
    2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2019, : 1587 - 1594