MethaneSET-L89 Pretraining: Plume-Free Landsat 8/9 Scenes for Self-Supervised Learning
methaneset-l89-pretraining is the plume-free subset of MethaneSET-L89, designed for self-supervised pretraining of methane detection models. This subset contains Landsat 8/9 imagery from locations and time periods where no methane plumes were detected, providing clean background scenes for learning spectral representations of oil/gas infrastructure, geological features, and atmospheric conditions without methane signatures. Unlike MARS-S2L which provides only six common bands, MethaneSET retrieves all 9 Landsat OLI bands at 10m GSD (200x200 pixel chips), enabling research with coastal aerosol, cirrus, and panchromatic channels. Each sample includes target and reference image pairs, Cloud Score+ masks, wind vectors (ERA5-Land onshore, GEOS-FP offshore), solar/viewing geometry, elevation (Copernicus DEM GLO-30), and 64-dim AlphaEarth Foundation embeddings.
If you use this dataset in your research, please cite:
DOI: 10.48550/arXiv.2411.15452
Vaughan, A., Mateo-Garcia, G., Irakulis-Loitxate, I., Watine, M., Fernandez-Poblaciones, P., Turner, R. E., Requeima, J., Gorroño, J., Randles, C., Caltagirone, M., & Cifarelli, C.* (2024). AI for operational methane emitter monitoring from space. arXiv preprint arXiv:2411.15452.
Operational MARS-S2L system for global methane monitoring from Sentinel-2 and Landsat 8/9.
DOI: 10.48550/arXiv.2511.21777
Vaughan, A., Mateo-Garcia, G., Irakulis-Loitxate, I., Watine, M., Fernandez-Poblaciones, P., Turner, R. E., Requeima, J., Gorroño, J., Randles, C., Caltagirone, M., & Cifarelli, C.* (2024). Artificial intelligence for methane detection: from continuous monitoring to verified mitigation. arXiv preprint arXiv:2511.21777.
Extended operational deployment demonstrating 1,015 stakeholder notifications across 20 countries and verified permanent mitigation of six persistent emitters.
DOI: 10.5194/essd-13-4349-2021
Muñoz-Sabater, J., et al. (2021). ERA5-Land: a state-of-the-art global reanalysis. Earth System Science Data, 13, 4349-4383.
DOI: 10.1029/2014JD022685
Lucchesi, R. (2013). GEOS-5 FP (Forward Processing) File Specification. NASA GMAO Technical Report.