Skip to main content

By Kyoto University

As global temperatures rise to record highs, the pressure to curb greenhouse gas emissions has intensified. Methane is particularly targeted because its significant global-warming potential in the short term exceeds carbon dioxide by over 80-fold.

However, monitoring methane emissions and compiling their quantities have been challenging due to limiting trade-offs with existing detection methods.

Now, a research team including Kyoto University and Geolabe, USA has developed a method to automatically detect methane emissions at a global scale. The work is published in the journal Nature Communications.

“Our approach can potentially provide methane detection at high frequency and high resolution from point sources, paving the way for a systematic quantification method,” says lead author Bertrand Rouet-Leduc of KyotoU’s Disaster Prevention Research Institute and Geolabe.

Rouet-Leduc further suggests that their method may help prioritize and automatically validate atmospheric mitigation of methane, which currently accounts for approximately one third of global warming.

Multispectral satellite data has emerged as a viable methane detection tool in recent years, enabling routine measurements of methane plumes at a global scale every few days. However, significant noise plagues these methane data, and until now, detections have been limited to very large emissions and have required human verification.

In contrast, the team has trained an AI to automatically detect methane leaks over 200kg/h, accounting for over 85% of the methane emissions in well-studied, large oil and gas basins.

“With satellite measurements, trade-offs must be made between spatial coverage, spatial and temporal resolution, and spectral resolution and associated detection accuracy. AI partially offsets these trade-offs,” explains co-author Claudia Hulbert, also of Geolabe.

Methane plumes are invisible and odorless, so they are typically detected with specialized equipment such as infrared cameras. The difficulty in finding these leaks from space goes without saying, akin to finding a needle in a haystack. Leaks are distributed around the globe, and most of the methane plumes are relatively small, making them easy to miss in satellite data.

The group’s collaborative work represents a key step towards the precise, systematic monitoring of methane emissions, anywhere on Earth, every few days.

“Automation is paramount when analyzing large areas. We were surprised that AI can automate the process and dramatically outperform the human eye in detecting small methane plumes,” reflects Rouet-Leduc.

“In our next phase, we plan to integrate additional satellites in a global study of methane emissions.”

Methane emissions are a potent driver of global warming, yet their accurate detection is often a challenge, in particular when the leaks are small in volume. Talk with Bertrand Rouet-Leduc from Kyoto University, who employs a deep learning approach to detect previously unrecognizable, small methane leaks from Sentinel-2 data.

More information: Bertrand Rouet-Leduc et al, ‘Automatic detection of methane emissions in multispectral satellite imagery using a vision transformer’, Nature Communications (2024). DOI: 10.1038/s41467-024-47754-y. Kyoto University – Press Release Featured image: Methane plume emitting from oil and gas facility. AI to automatically detect global methane emissions in satellite imagery. Credit: Bertrand Rouet-Leduc / Kyoto University

Carbon dioxide removal: feasibility study evaluates possible measures for Germany
Carbon dioxide removal: feasibility study evaluates possible measures for GermanyScience

Carbon dioxide removal: feasibility study evaluates possible measures for Germany

By Helmholtz Association of German Research Centres Germany aims to be climate neutral by 2045. In order to achieve this goal, greenhouse gas emissions must…
SourceSourceMay 16, 2024 Full article
Planetary boundary layer revealed: satellites illuminate atmospheric mysteries
Image: View of Earth and satellite
Planetary boundary layer revealed: satellites illuminate atmospheric mysteriesScience

Planetary boundary layer revealed: satellites illuminate atmospheric mysteries

Unlocking the secrets of Earth's planetary boundary layer (PBL), a pivotal zone influencing air quality and climate, a new study offers unprecedented insights into atmospheric…
SourceSourceJune 18, 2024 Full article
Long-distance relationship revealed in the seemingly random behavior of bowhead whales
Bowhead whale and calf in the Arctic Ocean
Long-distance relationship revealed in the seemingly random behavior of bowhead whalesScience

Long-distance relationship revealed in the seemingly random behavior of bowhead whales

By Hokkaido University, Aarhus University & Greenland Institute of Natural Resources Applying chaos theory to the movement of iconic arctic whales uncovered a 24-hour diving…
SourceSourceAugust 11, 2024 Full article