Automatic detection of methane emissions in multispectral satellite imagery using a vision transformer
Problem
Detecting methane point-source emissions from satellites was limited by trade-offs between coverage, resolution and detection accuracy.
Why it matters
Curbing methane emissions is among the most effective actions to slow global warming, but monitoring has been incomplete.
What the AI did
A deep learning model (vision transformer) overcame the spectral-resolution trade-off in multispectral Sentinel-2 data, enabling methane plume detection with global coverage and high spatio-temporal resolution.
Results
Detects plumes down to 0.01 km², corresponding to 200–300 kg CH4/h sources; order of magnitude improvement over state-of-the-art.
Impact
Peer-reviewed tool validated against airborne methane campaigns, a step toward automated global high-resolution emission detection.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Bertrand Rouet‐Leduc, Claudia Hulbert |
| Citations | 91 (OpenAlex, at import time) |
| References | 35 |
| Model or method | vision transformer |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-024-47754-y |
| Open access | gold |
| Keywords | methane detection, satellite imagery, vision transformer, Sentinel-2, deep learning, emissions monitoring |
Importance rating
major — millions of lives, an industry or a field
Abstract states curbing methane emissions is among the most effective actions to slow global warming; tool enables automated global high-resolution detection, an order of magnitude over state-of-the-art.
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|