IAS-Seminar: Representation learning for the Earth Sciences

Referent: Christian Lessig, Institute for Simulation and Graphics, Universität Magdeburg

Representation learning, where the objective is to obtain a domain specific but task independent neural network model, has so far received little attention in scientific machine learning and in the Earth system sciences. I will explain why spatio-temporal representation learning provides a promising direction for data-driven modeling of dynamical systems, in particular highly complex ones such as the atmosphere or the oceans. I will also discuss why transformers are a natural choice as the underlying neural network model. Results are presented for representation learning of ideal hyperbolic systems and fluid flows. For real atmospheric data, I will present how representation learning can lead to data-driven loss functions that improve the training for applications such as machine learned downscaling. 

This talk was also recorded, see video.