AI for operational methane emitter monitoring from space

TL;DR

This paper introduces MARS-S2L, an AI-based system that uses satellite imagery to detect methane emissions globally, significantly improving detection accuracy and enabling real-time monitoring and notifications.

Contribution

The paper presents MARS-S2L, a novel AI-driven methane monitoring system that operates on Sentinel-2 and Landsat data, with a large global dataset and improved detection performance.

Findings

216% improvement in detection precision over previous methods

457 near-real-time detections in 22 countries over six months

Used to notify governments and stakeholders about methane emissions

Abstract

Mitigating methane emissions is the fastest way to stop global warming in the short-term and buy humanity time to decarbonise. Despite the demonstrated ability of remote sensing instruments to detect methane plumes, no system has been available to routinely monitor and act on these events. We present MARS-S2L, an automated AI-driven methane emitter monitoring system for Sentinel-2 and Landsat satellite imagery deployed operationally at the United Nations Environment Programme's International Methane Emissions Observatory. We compile a global dataset of thousands of super-emission events for training and evaluation, demonstrating that MARS-S2L can skillfully monitor emissions in a diverse range of regions globally, providing a 216% improvement in mean average precision over a current state-of-the-art detection method. Running this system operationally for six months has yielded 457 near-real-time detections in 22 different countries of which 62 have already been used to provide formal notifications to governments and stakeholders.