Machine learning can be applied to remote sensing data to infer climate-relevant information such as global greenhouse gas emissions, building footprints, solar panel locations, or occurrences of deforestation.[1] Some general-purpose remote sensing datasets are listed below.
Satellite imagery datasets
High-resolution RGB satellite images (for visual predictions)
Public datasets
- United States Geological Survey
- Copernicus (Sentinel satellites)
- NASA Worldview
- Google Earth (permission needed for research use)
Commercial datasets
- DigitalGlobe (up to 31cm resolution)
- Planet (up to 72cm resolution)
Multispectral satellite images (5-13 visible and infrared bands)
Public datasets
Commercial datasets
Hyperspectral satellite images (up to a few hundred visible and infrared bands):
Public datasets
See also
- Table 1 of the review "Survey of Hyperspectral Earth Observation Applications from Space in the Sentinel-2 Context"[2] for comparisons between sources.
Street view datasets
References
- ↑ "Tackling climate change in the EU". Climate Change and Law Collection.
- ↑ Transon, Julie; d’Andrimont, Raphaël; Maugnard, Alexandre; Defourny, Pierre (2018-01-23). "Survey of Hyperspectral Earth Observation Applications from Space in the Sentinel-2 Context". Remote Sensing. 10 (3): 157. doi:10.3390/rs10020157. ISSN 2072-4292.