Year: 2026
Type: preprint
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 \ours, 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 15-day ensemble forecast in 3 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.
Source: arXiv (Cornell University)
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
SDG: Climate action
Open Access status: green
Awards: SCH: MS-ADAPT: Multi-Sensor Adaptive Data Analytics for Physical Therapy, CAREER: The Large-scale Buffering of Shallow Cloud Perturbations, G5031980239, Collaborative Research: SCALE MoDL: Representation Theoretic Foundations of Deep Learning, G7452299184, CAREER: New Frontiers In Large-Scale Spatiotemporal Data Analysis, G962744442
OpenAlex ID: W7154173042
