Sparse InSAR Data 3D Inpainting for Ground Deformation Detection Along the Rail Corridor

TL;DR

This paper introduces a novel method for inpainting sparse and noisy InSAR data to create dense ground deformation maps, enhancing the detection of ground movement near rail corridors.

Contribution

The study proposes a new scheme for processing sparse, noisy InSAR data into dense spatio-temporal stacks, facilitating improved ground deformation analysis.

Findings

Effective noise suppression in InSAR data

Enhanced ground deformation detection accuracy

Potential for deep learning applications

Abstract

Monitoring of ground movement close to the rail corridor, such as that associated with landslips caused by ground subsidence and/or uplift, is of great interest for the detection and prevention of possible railway faults. Interferometric synthetic-aperture radar (InSAR) data can be used to measure ground deformation, but its use poses distinct challenges, as the data is highly sparse and can be particularly noisy. Here we present a scheme for processing and interpolating noisy, sparse InSAR data into a dense spatio-temporal stack, helping suppress noise and opening up the possibility for treatment with deep learning and other image processing methods.