Fig. 1
From: 3D volumetric tomography of clouds using machine learning for climate analysis
Spaceborne cloud tomography. In CloudCT, a coordinated satellite formation acquires images. Our learning-based tomography model processes the images. The model infers the posterior probability distribution of the cloud extinction coefficient at any point in a 3D domain. It thus infers a volumetric map of probability distributions (a distribution per location). The probability distribution yields multiple products, such as 3D maps of the cloud extinction coefficient’s most probable value and uncertainty, precipitation forecast, or ground-level solar power. The globe image was taken from the source pixabay.com/photos/earth-globe-planet-world-space-11015.
