An Unsupervised Generative Neural Approach for InSAR Phase Filtering and Coherence Estimation

Abstract

Earth's physical properties like atmosphere, topography and ground instability can be determined by differencing billions of phase measurements (pixels) in subsequent matching Interferometric Synthetic Aperture Radar (InSAR) images. Quality (coherence) of each pixel can vary from perfect information (1) to complete noise (0), which needs to be quantified, alongside filtering information-bearing pixels. Phase filtering is thus critical to InSAR's Digital Elevation Model (DEM) production pipeline, as it removes spatial inconsistencies (residues), immensely improving the subsequent unwrapping. Recent explosion in quantity of available InSAR data can facilitate Wide Area Monitoring (WAM) over several geographical regions, if effective and efficient automated processing can obviate manual quality-control. Advances in parallel computing architectures and Convolutional Neural Networks (CNNs) which thrive on them to rival human performance on visual pattern recognition makes this approach ideal for InSAR phase filtering for WAM, but remains largely unexplored. We propose "GenInSAR", a CNN-based generative model for joint phase filtering and coherence estimation. We use satellite and simulated InSAR images to show overall superior performance of GenInSAR over five algorithms qualitatively, and quantitatively using Phase and Coherence Root-Mean-Squared-Error, Residue Reduction Percentage, and Phase Cosine Error.

A CNN-Based Coherence-Driven Approach for InSAR Phase Unwrapping

“…This approach has already been investigated in the literature, showing a high potential when applied in a supervised manner [20]. Moreover, as shown in [21], an unsupervised learning approach could also help to overcome training problems caused by the scarcity of data, which is a common issue in remote-sensing applications.…”

Identification of Surface Deformation in InSAR Using Machine Learning

“…In automated event detection, atmospheric noise limits the minimum detectable surface deformation by the CNN. Research into noise reduction in InSAR using CNN‐based autoencoders is necessary for CNNs to be capable of classification of small surface deformation (e.g., Mukherjee et al., 2020).…”

“…Currently Mukherjee et al. (2020) as well as other unpublished work are addressing atmospheric and phase effects in InSAR, which is a key problem in accurate detection and classification of small deformation signals.…”

“…For example, Anantrasirichai et al (2018Anantrasirichai et al ( , 2019aAnantrasirichai et al ( , 2019b and Valade et al (2019) adapt a pretrained CNN to classify sustained volcanic deformation in InSAR, and Anantrasirichai et al (2020) adapted a pretrain CNN to detect ground deformation associated mining, landslides, and dewatering. Currently Mukherjee et al (2020) as well as other unpublished work are addressing atmospheric and phase effects in InSAR, which is a key problem in accurate detection and classification of small deformation signals.…”

IGS-CMAES: A Two-Stage Optimization for Ground Deformation and DEM Error Estimation in Time Series InSAR Data

“…Our main focus is studying parameter estimation of linear deformation rate and DEM error upon PS time series, for the following reasons. (1) There are many state-of-the-art methods for filtering random noise and suppressing atmosphere components from a stack of interferograms [25,27,[32][33][34]. (2) Recently, satellite facilities can provide accurate enough orbits for practical usage [35][36][37].…”