Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
This work addresses the need for accurate uncertainty quantification in weather forecasting, which is crucial for meteorologists and decision-makers, though it appears incremental by building on existing graph-based methods.
The authors tackled the problem of probabilistic weather forecasting by proposing Graph-EFM, a model that combines latent-variable formulation with graph-based frameworks to efficiently generate spatially coherent ensembles, achieving equivalent or lower errors than deterministic models while capturing uncertainty.
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.