{GSR4B}: Biomass Map Super-Resolution with Sentinel-1/2 Guidance

2025-04-02

AI Summary

Addressing the challenge of generating global high-resolution aboveground biomass (AGB) maps—where existing satellite-derived products (e.g., ESA CCI AGB) suffer from coarse spatial resolution (100 m), while airborne LiDAR is prohibitively expensive and spatially limited—this work proposes the first Guided Super-Resolution (GSR) framework specifically designed for AGB mapping. Methodologically, it leverages multi-source high-resolution Sentinel-1 (SAR) and Sentinel-2 (optical) imagery as guidance, fuses SAR and optical features, and introduces a Multi-Scale Guidance (MSG) strategy to replace conventional RGB+Depth paradigms, enabling an end-to-end deep learning-based super-resolution network that upscales 100 m AGB maps to 10 m. Experiments on the BioMassters dataset demonstrate a 780 t/ha reduction in RMSE and a 2.0 dB PSNR improvement, notably enhancing reconstruction accuracy in high-biomass regions without significant computational overhead. The code and trained models are publicly released.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Semi-Supervised Learning
• Multiagent Systems: Multiagent Learning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Accurate Above-Ground Biomass (AGB) mapping at both large scale and high spatio-temporal resolution is essential for applications ranging from climate modeling to biodiversity assessment, and sustainable supply chain monitoring. At present, fine-grained AGB mapping relies on costly airborne laser scanning acquisition campaigns usually limited to regional scales. Initiatives such as the ESA CCI map attempt to generate global biomass products from diverse spaceborne sensors but at a coarser resolution. To enable global, high-resolution (HR) mapping, several works propose to regress AGB from HR satellite observations such as ESA Sentinel-1/2 images. We propose a novel way to address HR AGB estimation, by leveraging both HR satellite observations and existing low-resolution (LR) biomass products. We cast this problem as Guided Super-Resolution (GSR), aiming at upsampling LR biomass maps (sources) from $100$ to $10$ m resolution, using auxiliary HR co-registered satellite images (guides). We compare super-resolving AGB maps with and without guidance, against direct regression from satellite images, on the public BioMassters dataset. We observe that Multi-Scale Guidance (MSG) outperforms direct regression both for regression ($-780$ t/ha RMSE) and perception ($+2.0$ dB PSNR) metrics, and better captures high-biomass values, without significant computational overhead. Interestingly, unlike the RGB+Depth setting they were originally designed for, our best-performing AGB GSR approaches are those that most preserve the guide image texture. Our results make a strong case for adopting the GSR framework for accurate HR biomass mapping at scale. Our code and model weights are made publicly available (https://github.com/kaankaramanofficial/GSR4B).

Problem

• Enabling high-resolution global biomass mapping
• Upsampling low-resolution biomass maps using satellite data
• Improving accuracy of above-ground biomass estimation

Innovation

• Guided Super-Resolution for biomass mapping
• Multi-Scale Guidance improves accuracy
• Leverages Sentinel-1/2 and low-resolution data