A Deep Learning Application for Deformation Prediction from Ground-Based InSAR

Abstract

Ground-based synthetic aperture radar interferometry (GB-InSAR) has the characteristics of high precision, high temporal resolution, and high spatial resolution, and is widely used in highwall deformation monitoring. The traditional GB-InSAR real-time processing method is to process the whole data set or group in time sequence. This type of method takes up a lot of computer memory, has low efficiency, cannot meet the timeliness of slope monitoring, and cannot perform deformation prediction and disaster warning forecasting. In response to this problem, this paper proposes a GB-InSAR time series processing method based on the LSTM (long short-term memory) model. First, according to the early monitoring data of GBSAR equipment, the time series InSAR method (PS-InSAR, SBAS, etc.) is used to obtain the initial deformation information. According to the deformation calculated in the previous stage and the atmospheric environmental parameters monitored, the LSTM model is used to predict the deformation and atmospheric delay at the next time. The phase is removed from the interference phase, and finally the residual phase is unwrapped using the spatial domain unwrapping algorithm to solve the residual deformation. The predicted deformation and the residual deformation are added to obtain the deformation amount at the current moment. This method only needs to process the difference map at the current moment, which greatly saves time series processing time and can realize the prediction of deformation variables. The reliability of the proposed method is verified by ground-based SAR monitoring data of the Guangyuan landslide in Sichuan Province.

Analysis and Prediction of Urban Surface Transformation Based on Small Baseline Subset Interferometric Synthetic Aperture Radar and Sparrow Search Algorithm–Convolutional Neural Network–Long Short-Term Memory Model

“…Input phase: Selective forgetting of information from the previous moment’s input message is performed [ 41 ]. Whether the input is forgotten or not is controlled by the forgetting gating , which controls the previous moment’s cell state, .…”

Deformation extraction of building facade using ground-based interferometric synthetic aperture radar assisted by 3D laser scanning technology

“…At the same time, limitations in site setup conditions, construction factors, or human errors can also lead to non-horizontal radar sensor attitudes and operational tracks. Furthermore, the tilting of the ground-based real-aperture radar [10], the inclination of linear GB-SAR guiding tracks, and the tilting of the imaging projection surface due to the rotation plane of ArcSAR [11,12] and the inclination of feed antenna panels can all result in the tilting of the imaging projection surface. These numerous factors prevent radar sensors from achieving an ideal horizontal attitude, directly impacting the accurate identification of the positions of building structural deformations in close to medium range.…”

Potential Landslide Identification Based on Improved YOLOv8 and InSAR Phase-Gradient Stacking

“…In recent years, with the significant development of deep learning, it has achieved remarkable performance in the field of computer vision and has been applied to InSAR phase unwrapping [12]- [13], decorrelation masking [14], and time series deformation prediction [15][16]. Particularly in the task of identifying potential landslides with InSAR, InSAR technology accurately generates deformation feature maps of target areas from time series SAR image data, providing data support for training deep learning neural network models.…”