Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
Abstract
In recent years, machine learning has established itself as a powerful tool for high-resolution weather forecasting. While most current machine learning models focus on deterministic forecasts, accurately capturing the uncertainty in the chaotic weather system calls for probabilistic modeling. We propose a probabilistic weather forecasting model called Graph-EFM, combining a flexible latent-variable formulation with the successful graph-based forecasting framework. The use of a hierarchical graph construction allows for efficient sampling of spatially coherent forecasts. Requiring only a single forward pass per time step, Graph-EFM allows for fast generation of arbitrarily large ensembles. We experiment with the model on both global and limited area forecasting. Ensemble forecasts from Graph-EFM achieve equivalent or lower errors than comparable deterministic models, with the added benefit of accurately capturing forecast uncertainty.
Cite
@article{arxiv.2406.04759,
title = {Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks},
author = {Joel Oskarsson and Tomas Landelius and Marc Peter Deisenroth and Fredrik Lindsten},
journal= {arXiv preprint arXiv:2406.04759},
year = {2024}
}
Comments
72 pages, 33 figures. NeurIPS 2024. Code is available at https://github.com/mllam/neural-lam/tree/prob_model_global (global forecasting) and https://github.com/mllam/neural-lam/tree/prob_model_lam (limited area modeling)