IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing | |
Use of LSTM for Sinkhole-Related Anomaly Detection and Classification of InSAR Deformation Time Series | |
Ling Chang1  Alfred Stein1  Anurag Kulshrestha1  | |
[1] Department of Earth Observation Science, Faculty of Geoinformation Science and Earth Observation (ITC), University of Twente, Enschede, AE, The Netherlands; | |
关键词: Anomaly detection; breakpoint; heaviside; long short term memory (LSTM); sinkholes; time-series classification; | |
DOI : 10.1109/JSTARS.2022.3180994 | |
来源: DOAJ |
【 摘 要 】
Sinkholes exhibit precursory deformation patterns. Such deformation patterns can be studied using InSAR time-series analysis over constantly coherent scatterrers (CCS). In the past we identified Heaviside and Breakpoint changes as two important forms of anomalous behavior. It is challenging to efficiently detect and classify these sudden step and sudden velocity changes in deformation time series, especially in the presence of tens of thousands CCS. To address this challenge, we propose to classify these forms of anomalous behavior with a deep learning-based supervised time series classification. In this study, we used a two-layered bidirectional long short term memory (LSTM) classification model for this purpose. The classified deformation classes were analyzed as well in the context of scattering mechanisms. We implemented this model on a sinkhole affected region spanning
【 授权许可】
Unknown