Towards Methane Detection Onboard Satellites
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916005801885696 |
|---|---|
| author | Chen, Maggie Lamdouar, Hala Marini, Luca Martínez-Ferrer, Laura Bridges, Chris Acciarini, Giacomo |
| author_facet | Chen, Maggie Lamdouar, Hala Marini, Luca Martínez-Ferrer, Laura Bridges, Chris Acciarini, Giacomo |
| contents | Methane is a potent greenhouse gas and a major driver of climate change, making its timely detection critical for effective mitigation. Machine learning (ML) deployed onboard satellites can enable rapid detection while reducing downlink costs, supporting faster response systems. Conventional methane detection methods often rely on image processing techniques, such as orthorectification to correct geometric distortions and matched filters to enhance plume signals. We introduce a novel approach that bypasses these preprocessing steps by using \textit{unorthorectified} data (UnorthoDOS). We find that ML models trained on this dataset achieve performance comparable to those trained on orthorectified data. Moreover, we also train models on an orthorectified dataset, showing that they can outperform the matched filter baseline (mag1c). We release model checkpoints and two ML-ready datasets comprising orthorectified and unorthorectified hyperspectral images from the Earth Surface Mineral Dust Source Investigation (EMIT) sensor at https://huggingface.co/datasets/SpaceML/UnorthoDOS , along with code at https://github.com/spaceml-org/plume-hunter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00626 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Methane Detection Onboard Satellites Chen, Maggie Lamdouar, Hala Marini, Luca Martínez-Ferrer, Laura Bridges, Chris Acciarini, Giacomo Computer Vision and Pattern Recognition Artificial Intelligence Methane is a potent greenhouse gas and a major driver of climate change, making its timely detection critical for effective mitigation. Machine learning (ML) deployed onboard satellites can enable rapid detection while reducing downlink costs, supporting faster response systems. Conventional methane detection methods often rely on image processing techniques, such as orthorectification to correct geometric distortions and matched filters to enhance plume signals. We introduce a novel approach that bypasses these preprocessing steps by using \textit{unorthorectified} data (UnorthoDOS). We find that ML models trained on this dataset achieve performance comparable to those trained on orthorectified data. Moreover, we also train models on an orthorectified dataset, showing that they can outperform the matched filter baseline (mag1c). We release model checkpoints and two ML-ready datasets comprising orthorectified and unorthorectified hyperspectral images from the Earth Surface Mineral Dust Source Investigation (EMIT) sensor at https://huggingface.co/datasets/SpaceML/UnorthoDOS , along with code at https://github.com/spaceml-org/plume-hunter. |
| title | Towards Methane Detection Onboard Satellites |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.00626 |