Self-Supervised Super-Resolution for Sentinel-5P Hyperspectral Images

TL;DR

This paper introduces a self-supervised super-resolution framework for Sentinel-5P hyperspectral images, enabling high-quality spatial resolution enhancement without requiring true high-resolution ground truth data.

Contribution

It combines Stein's Unbiased Risk Estimator with an equivariant imaging constraint and efficient U-Net architectures for effective self-supervised hyperspectral super-resolution.

Findings

Self-supervised models perform comparably to supervised methods.

Enhanced spatial detail over bicubic interpolation.

Physically meaningful structures validated with EMIT data.

Abstract

Sentinel-5P (S5P) plays a critical role in atmospheric monitoring; however, its spatial resolution limits fine-scale analysis. Existing super-resolution (SR) approaches rely on supervised learning with synthetic low-resolution (LR) data, since true high-resolution (HR) data do not exist, limiting their applicability to real observations. We propose a self-supervised hyperspectral SR framework for S5P that enables training without HR ground truth. The method combines Stein's Unbiased Risk Estimator (SURE) with an equivariant imaging constraint, incorporating the S5P degradation operator and noise statistics derived from signal-to-noise ratio (SNR) metadata. We also introduce depthwise separable convolution U-Net architectures designed for efficiency and spectral fidelity. The framework is evaluated in two settings: (i) LR-HR, where synthetic LR data are used for direct comparison with supervised learning, and (ii) GT-SHR, where super-resolved images surpass the native spatial resolution without HR reference. Results across multiple bands show that self-supervised models achieve performance comparable to supervised methods while maintaining strong consistency. Qualitative analysis shows improved spatial detail over bicubic interpolation, and validation with EMIT data confirms that reconstructed structures are physically meaningful. Code is available at https://github.com/hyamomar/Sentinel-5P-Super-Resolution/tree/main/self_supervised