U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
2026-04-10 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors show that very complex AI models are not needed for good weather forecasts. They created U-Cast, which uses a commonly known AI design called U-Net and a simple two-step training process. Their model predicts weather as well as top systems but uses much less computing power and is faster. This means more people can build advanced weather prediction tools without expensive resources.
AI weather forecastingU-Netprobabilistic forecastingMean Absolute ErrorContinuous Ranked Probability ScoreMonte Carlo Dropoutensemble forecastcompute efficiencytraining curriculum
Authors
Salva Rühling Cachay, Duncan Watson-Parris, Rose Yu
Abstract
AI-based weather forecasting now rivals traditional physics-based ensembles, but state-of-the-art (SOTA) models rely on specialized architectures and massive computational budgets, creating a high barrier to entry. We demonstrate that such complexity is unnecessary for frontier performance. We introduce U-Cast, a probabilistic forecaster built on a standard U-Net backbone trained with a simple recipe: deterministic pre-training on Mean Absolute Error followed by short probabilistic fine-tuning on the Continuous Ranked Probability Score (CRPS) using Monte Carlo Dropout for stochasticity. As a result, our model matches or exceeds the probabilistic skill of GenCast and IFS ENS at 1.5$^\circ\$ resolution while reducing training compute by over 10$\times$ compared to leading CRPS-based models and inference latency by over 10$\times$ compared to diffusion-based models. U-Cast trains in under 12 H200 GPU-days and generates a 60-step ensemble forecast in 11 seconds. These results suggest that scalable, general-purpose architectures paired with efficient training curricula can match complex domain-specific designs at a fraction of the cost, opening the training of frontier probabilistic weather models to the broader community. Our code is available at: https://github.com/Rose-STL-Lab/u-cast.