Towards probabilistic Weather Forecasting with Conditioned Spatio-Temporal Normalizing Flows

arXiv:2311.06958v2 Announce Type: replace
Abstract: Generative normalizing flows are able to model multimodal spatial distributions, and they have been shown to model temporal correlations successfully as well. These models provide several benefits over other types of generative models due to their training stability, invertibility and efficiency in sampling and inference. This makes them a suitable candidate for stochastic spatio-temporal prediction problems, which are omnipresent in many fields of sciences, such as earth sciences, astrophysics or molecular sciences. In this paper, …

abstract arxiv benefits correlations cs.ai cs.lg efficiency forecasting generative generative models inference multimodal sampling spatial stability temporal training type types weather weather forecasting