DeepInSAR—A Deep Learning Framework for SAR Interferometric Phase Restoration and Coherence Estimation

Xinyao Sun,Parwant Ghuman,Subhayan Mukherjee,Navaneeth Kamballur Kottayil,Aaron Zimmer,Irene Cheng

doi:10.3390/rs12142340

Abstract

Over the past decade, using Interferometric Synthetic Aperture Radar (InSAR) remote sensing technology for ground displacement detection has become very successful. However, during the acquisition stage, microwave signals reflected from the ground and received by the satellite are contaminated, for example, due to undesirable material reflectance and atmospheric factors, and there is no clean ground truth to discriminate these noises, which adversely affect InSAR phase computation. Accurate InSAR phase filtering and coherence estimation are crucial for subsequent processing steps. Current methods require expert supervision and expensive runtime to evaluate the quality of intermediate outputs, limiting the usability and scalability in practical applications, such as wide area ground displacement monitoring and predication. We propose a deep convolutional neural network based model DeepInSAR to intelligently solve both phase filtering and coherence estimation problems. We demonstrate our model’s performance using simulated and real data. A teacher-student framework is introduced to handle the issue of missing clean InSAR ground truth. Quantitative and qualitative evaluations show that our teacher-student approach requires less input but can achieve better results than its stack-based teacher method even on new unseen data. The proposed DeepInSAR also outperforms three other top non-stack based methods in time efficiency without human supervision.

Highlights

Synthetic Aperture Radar (SAR) is a remote sensing technology, which uses active microwaves to capture ground surface characteristics
Ground truth is treated as an optimal teacher for training our proposed DeepInSAR; we can objectively demonstrate our model’s capability to learn proper phase filtering and coherence estimation for new simulated testing images, with ground truth available
We propose a learning-based DeepInSAR framework to address two important research issues: Interferometric SAR (InSAR) phase filtering and coherence estimation, in a single process

Summary

Introduction

Synthetic Aperture Radar (SAR) is a remote sensing technology, which uses active microwaves to capture ground surface characteristics. Each pixel in an interferogram indicates phase difference between two co-registered SLC images. The phase difference encodes useful information including deformation of the earth’s surface and topographical signals, and has been successfully used to obtain the digital elevation model (DEM). Noisy SAR images make the interferometric phase filtering step on their output InSAR image more challenging. Restoration of interferometric phase image becomes a fundamental and crucial step to ensure measurement accuracy in remote sensing. In this regard, the coherence map of interferogram is a crucial indicator showing reliability of the interferometric phase [3]. Interferometric phase filtering and coherence estimation are the main focus in this work

Objectives

Methods

Results

Discussion

Conclusion