Deep Learning-Based Damage Mapping With InSAR Coherence Time Series

Abstract

Satellite remote sensing is playing an increasing role in the rapid mapping of damage after natural disasters. In particular, synthetic aperture radar (SAR) can image the Earth's surface and map damage in all weather conditions, day and night. However, current SAR damage mapping methods struggle to separate damage from other changes in the Earth's surface. In this study, we propose a novel approach to damage mapping, combining deep learning with the full time history of SAR observations of an impacted region in order to detect anomalous variations in the Earth's surface properties due to a natural disaster. We quantify Earth surface change using time series of interferometric SAR coherence, then use a recurrent neural network (RNN) as a probabilistic anomaly detector on these coherence time series. The RNN is first trained on preevent coherence time series, and then forecasts a probability distribution of the coherence between pre-and post-event SAR images. The difference between the forecast and observed coevent coherence provides a measure of confidence in the identification of damage. The method allows the user to choose a damage detection threshold that is customized for each location, based on the local behavior of coherence through time before the event. We apply this method to calculate estimates of damage for three earthquakes using multiyear time series of Sentinel-1 SAR acquisitions. Our approach shows good agreement with observed damage and quantitative improvement compared to using preto co-event coherence loss as a damage proxy.

Machine‐Learning Estimation of Snow Depth in 2021 Texas Statewide Winter Storm Using SAR Imagery

“…Urban areas with manmade structures usually maintain stable phase values during time and thus represent high coherence. However, this theory does not sustain in the condition of land cover alternations such as from the snow (Stephenson et al., 2021). Volumetric decorrelation occurs in snowpack in any land covers.…”

‘Nowhere and no one is safe’: spatial analysis of damage to critical civilian infrastructure in the Gaza Strip during the first phase of the Israeli military campaign, 7 October to 22 November 2023

“…NASA ARIA emergency response data products), and rests on the measurement of changes in coherence, which is the similarity between phase components of interferometric radar waves collected over different points in time [ 26 ]. Stable coherence over time in a built-up environment like the Gaza Strip suggests the persistent presence of a feature, such as a building [ 27 ], while a large and persistent decrease in coherence from one image date to the next suggests structural damage or destruction [ 28 , 29 ]. Native resolution Sentinel-1 data acquired in the interferometric-wide swath mode have a spatial resolution of 5 m by 20 m in range and azimuth (radar geometries), which, when projected onto a geospatial grid in ground range, results in a 10 m pixel spacing product.…”

Earth Observation to Address Inequities in Post‐Flood Recovery

“…The diversity in the spectral resolution of EO enables applications unrestricted by cloud cover that thwarts optical imagery. Interferometric synthetic aperture radar is used to detect anomalous changes in surface backscatter to map post‐disaster damage (Plank, 2014; Stephenson et al., 2022). InSAR has been used in Damage Proxy Maps (e.g., Yun et al., 2015) to rapidly detect damage in urban contexts to support rapid response efforts by groups like NASA Advanced Rapid Imaging and Analysis (ARIA).…”