Detecting slow-moving landslides using InSAR phase-gradient stacking and deep-learning network

Abstract

Landslides are a major geohazard that endangers human lives and properties. Recently, efforts have been made to use Synthetic Aperture Radar Interferometry (InSAR) for landslide monitoring. However, it is still difficult to effectively and automatically identify slow-moving landslides distributed over a large area due to phase unwrapping errors, decorrelation, troposphere turbulence and computational requirements. In this study, we develop a new approach combining phase-gradient stacking and a deep-learning network based on YOLOv3 to automatically detect slow-moving landslides from large-scale interferograms. Using Sentinel-1 SAR images acquired from 2014 to 2020, we developed a burst-based, phase-gradient stacking algorithm to sum up phase gradients in short-temporal-baseline interferograms along the azimuth and range directions. The stacked phase gradients clearly reveal the characteristics of localized surface deformation that is mainly caused by slow-moving landslides and avoids the errors due to phase unwrapping in partially decorrelated areas and atmospheric effects. Then, we trained the improved Attention-YOLOv3 network with stacked phase-gradient maps of manually labeled landslides to achieve quick and automatic detection. We applied our method in an ∼180,000 km2 area of southwestern China and identified 3,366 slow-moving landslides. By comparing the results with optical imagery and previously published landslides in this region, the proposed method can achieve automatic detection over a large area precisely and efficiently. From the derived landslide density map, we determined that most landslides are distributed along the three large rivers and their branches. In addition to some counties with known high-density landslides, approximately 10 more counties with high landslide density were exposed, which should attract more attention to their risks for geohazards. This application demonstrates the potential value of our newly developed method for slow-moving landslide detection over a nation-wide area, which can be employed before applying more time-consuming time-series InSAR analysis.

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

“…After each gradient calculation, the phase-gradient image is wrapped to ensure its values remain within the range of [-π, π). Subsequently, all interferometric phase-gradient images are stacked sequentially [10], followed by stacking all phase-gradient images and wrapping them to obtain the stacked results of phase-gradients in azimuth and range directions.…”

“…This paper has developed an improved YOLOv8 object detection model for Stacked phase-gradient dataset [10] shown in Fig. 3).…”

“…In the deformation velocity maps calculated by time-series InSAR, there are atmospheric errors and random noise errors. In comparison with velocity maps, interferometric phase-gradient calculates the phase difference between adjacent pixels [10], where the phase difference is mainly dominated by local deformation rather than the atmospheric delay with a larger non-correlated distance [11]. At the same time, stacking interferometric phase-gradients can effectively reduce the interference of random noise.…”

High‐Resolution Interseismic Strain Mapping From InSAR Phase‐Gradient Stacking: Application to the North Anatolian Fault With Implications for the Non‐Uniform Strain Distribution Related to Coseismic Slip Distribution

“…The phase gradient was first used to highlight strain concentrations on secondary fractures during the 1992 Landers earthquake (Sandwell & Price, 1998). By summing the phase gradients of multiple wrapped interferograms, the so‐called phase‐gradient stacking method has been applied to detect small fractures produced by the 2019 Ridgecrest earthquake (A. Xu et al., 2021; X. Xu et al., 2020) and to detect slow‐moving landslides with the deep‐learning network (Fu et al., 2022).…”

Automatic Detection of Forested Landslides: A Case Study in Jiuzhaigou County, China

“…Chen et al [34] proposed a semantic segmentation model with InSAR to identify active landslides. Fu et al [35] utilized YOLOv3 and InSAR phase-gradient layering to detect landslides that moved slowly. Nava et al [36] used a method of image classification based on deep learning to enhance landslide detection.…”