Beyond Backscatter: InSAR coherence from detected SAR images

2026-06-05

AI Summary

This study addresses the challenge of estimating InSAR coherence from widely available analysis-ready detected SAR imagery, which lacks the complex-valued data and precise coregistration traditionally required. To overcome this limitation, the authors propose a novel deep learning approach that accurately predicts InSAR coherence maps using only single-temporal SAR intensity images, without relying on complex data or strict coregistration. The method employs a Residual U-Net architecture trained with coherence maps derived from Sentinel-1 SLC data as supervision. Experimental results demonstrate that the model significantly outperforms existing intensity-based methods across diverse geographic regions and temporal baselines, exhibiting strong cross-domain generalization. Consequently, it can be directly deployed on global analysis-ready datasets, such as Sentinel-1 GRD products available in platforms like Google Earth Engine.

Abstract

In this work, we propose a deep learning framework for coherence regression directly from detected SAR images, without the need for accurate coregistration. A Residual U-Net is trained using coherence maps derived from precisely coregistered Sentinel-1 SLC data to learn the relationship between backscatter magnitudes and coherence. The model is trained on 12-day SLC pairs and evaluated across different datasets, including coregistered SLC products and open access analysis-ready data, covering diverse radiometric properties, geometries, and locations. Experimental results demonstrate that the proposed method achieves high-resolution coherence regression with improved accuracy compared to existing intensity-based approaches. The network generalizes well across diverse geographical locations and even across different temporal baselines that were never seen at training time. Additionally, the ability to operate on globally available analysis-ready data, such as ground range detected data, e.g., distributed through Google Earth Engine, enables its large-scale application in mission design, change monitoring, and diverse mapping tasks.

Problem

• InSAR coherence
• detected SAR images
• coregistration-free
• coherence estimation
• SAR backscatter

Innovation

• InSAR coherence
• deep learning
• detected SAR images
• Residual U-Net
• coregistration-free