Rapid and Automatic Detection of New Potential Landslide Based on Phase-Gradient DInSAR
Yue Shen, Keren Dai, Mingtang Wu, Guanchen Zhuo, Min Wang, Teng Wang, Qiang Xu
Abstract
Although the widely used time-series InSAR technology makes up for the shortcomings of traditional geological investigation, such as small coverage and low efficiency, it cannot achieve rapid and dynamic detection of new potential landslide due to its long data processing time and insensitivity to short-term new displacement. In this paper, a rapid method for automatically detection new potential landslides in wide area is proposed. Phase-gradient processing is performed based on the DInSAR results to automatically detect the potential landslide, in which the influence from geometric distortion, water, noise from low coherence area, and other errors are analyzed and removed. This method was performed in the Maoergai Reservoir Area where many potential landslides newly emerged during the impoundment period as the great water level fluctuations. As a result, 7 potential landslides with continuous deformation and relatively large deformation were detected. The error source was analyzed and removed. In the validation, an overall accuracy of up to 81% was achieved by comparing the results with the manual detection. This method provides a new way for rapid and automatic detection of new displacements in wide-area, especially for the area (e.g. reservoir area) with dynamic and rapid detection needs.