A Deep Learning Iterative Framework for Sentinel-1 Stripmap Enhancement Based on Azimuth Doppler Decomposition

2026-05-27

AI Summary

Sentinel-1 Stripmap SAR imagery is often degraded by speckle noise and imaging artifacts, limiting its utility in high-detail applications. To address this challenge, this work proposes a self-supervised deep learning enhancement framework that leverages the physical consistency between azimuth Doppler sub-aperture images and the full-aperture image to construct training pairs—eliminating the need for external data or simulated ground truth. The method integrates single-frame and multi-frame learning strategies and incorporates an iterative optimization-based inference mechanism. Evaluated on real Sentinel-1 data, the approach consistently outperforms MERLIN in both PSNR and SSIM metrics, achieving notably improved structural fidelity while maintaining scalability and practical deployability.

Abstract

Synthetic Aperture Radar (SAR) imagery enables all-weather, day-and-night Earth observation; however, it remains difficult to interpret due to speckle noise and other intrinsic imaging artifacts. Sentinel-1 (S1) constitutes one of the most widely used spaceborne SAR missions, offering systematic global coverage, high temporal resolution, dual-polarization imaging, and free data availability. Among S1 modes, Stripmap (SM) provides the highest resolution, yet speckle noise and spatial constraints often hinder applications requiring finer spatial detail. This motivates the need for effective image enhancement strategies. In this work, we propose a self-supervised enhancement framework for S1 SM imagery based on azimuth subaperture decomposition. The method exploits the physical consistency between subaperture reconstructions and the corresponding full-aperture image to generate paired training data without external sensors, simulated ground truth, or multi-temporal stacks. The proposed framework integrates single- and multi-frame learning and incorporates an iterative inference scheme that progressively refines image quality. Experiments on real S1 SM data show that the proposed approach consistently outperforms the widely adopted self-supervised deep learning baseline MERLIN, in terms of PSNR and SSIM, while MERLIN attains higher ENL, highlighting a trade-off between structural fidelity and speckle smoothing. Overall, the results demonstrate that subaperture-based supervision provides a physically grounded, reproducible, and operationally viable approach for SAR image enhancement using S1 data. It is worth noting that the proposed approach can be extended to other SAR platforms, polarizations, and acquisition modes.

Problem

• Sentinel-1
• Stripmap
• SAR image enhancement
• speckle noise
• spatial resolution

Innovation

• subaperture decomposition
• self-supervised learning
• iterative refinement
• SAR image enhancement
• Sentinel-1 Stripmap