Abstract

The radiative properties of clouds, and thus their impact on Earth’s climate, are significantly affected by how clouds spatially organise. The precise mechanisms which drive different forms of convective organisation are however currently unknown. With a tool to automatically classify regions into distinct forms of convective organisation it is possible to produce a statistical description of the most likely large-scale and local environmental conditions (e.g. windshear, horizontal convergence) present in differently organised states. And further, it will be possible to study their temporal evolution and quantify differences in behaviour of organisation in weather and climate models as compared to observations.

Using unsupervised learning of GOES -R imagery, I have developed machine learning model to automatically identify regimes of convective organisation in satellite imagery. I will show how this can be applied to study their radiative properties in the tropical Atlantic and the temporal evolution of marine stratocumulus.