A Fast Methane Detection Pipeline on Board Satellites Based on Mag1c-SAS and LinkNet

2026-06-02

AI Summary

This study addresses the challenges of high computational cost and reliance on manual region selection in conventional methane detection algorithms, which often lead to missed transient emissions under the resource-constrained conditions of on-orbit satellite systems. To overcome these limitations, this work proposes an efficient, low-power on-board methane detection pipeline that, for the first time, integrates the Adaptive Coherence Estimator (ACE) and Constrained Energy Minimization (CEM) into methane detection. The authors introduce Mag1c-SAS, an algorithm accelerated by 80×, combined with a lightweight LinkNet semantic segmentation model and two novel band selection strategies. Evaluated on the newly curated open-source datasets EMIT-MSeg and STARCOP, the method achieves over a 30-percentage-point improvement in AUPRC and approximately a 4-percentage-point gain in F1 score, while maintaining low CPU and RAM usage. The system is released as a lightweight PyPI library, balancing detection accuracy with practical feasibility for on-orbit deployment.

Abstract

Methane is a potent greenhouse gas, and detecting leaks early via hyperspectral satellite imagery can help climate change mitigation efforts. Meanwhile, many existing hyperspectral missions only capture areas manually targeted by operators, thus missing potential events of interest. To overcome slow downlink rates cost-effectively, onboard detection is a viable solution. However, traditional methane detection methods are too computationally demanding for resource-limited onboard hardware. This work accelerates methane detection by focusing on efficient, low-power algorithms. In particular, we test fast target detection ACE and CEM methods that have not been previously used for methane detection and propose Mag1c-SAS -- a significantly faster variant of the current state-of-the-art Mag1c algorithm. To explore their detection potential, we integrate them with a machine learning model based on U-Net and LinkNet. We evaluate our methods on the STARCOP dataset and a novel EMIT-MSeg dataset, which we introduce and open-source alongside a high-quality annotation strategy. The proposed Mag1c-SAS approach proves highly effective by operating ~80x faster than the original Mag1c approach, providing a visually similar, but noisier result. When additionally paired with the lightweight LinkNet approach, it effectively reduces noise, achieving AUPRC score improvements of over 30 pp on EMIT-MSeg compared to the baseline Mag1c approach, and an F1 score on STARCOP ~4 pp higher. We evaluate two novel band selection strategies and confirm the system's onboard viability through hardware profiling, demonstrating marginal power consumption and efficient CPU/RAM utilization. We release the final system in a user-friendly and lightweight PyPI library at: https://pypi.org/project/onboard-methane-detection/, alongside all experimental code, models, and data at: https://github.com/zaitra/methane-filters-benchmark.

Problem

• methane detection
• onboard processing
• hyperspectral imagery
• greenhouse gas
• satellite remote sensing

Innovation

• onboard methane detection
• Mag1c-SAS
• LinkNet
• hyperspectral imaging
• lightweight algorithm