U-Cast：一种惊人简单且高效的边界概率AI天气预报器
U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
AI总结：
提出基于标准U-Net骨架的概率天气预报模型U-Cast，通过确定性预训练和短时概率微调，以不到1/10的计算成本匹配或超越GenCast和IFS ENS的预报技能。
摘要：
基于AI的天气预报现在可以与传统的基于物理的集合预报相媲美，但最先进的模型依赖于专门的架构和巨大的计算预算，造成了很高的进入门槛。我们证明，对于边界性能而言，这种复杂性是不必要的。我们引入了\ours，一种基于标准U-Net骨架的概率预报器，采用简单的训练方案：先进行基于平均绝对误差的确定性预训练，然后使用蒙特卡洛Dropout引入随机性，基于连续排序概率评分（CRPS）进行短时概率微调。结果，我们的模型在$1.5^\circ$分辨率下匹配或超过了GenCast和IFS ENS的概率技能，同时与领先的基于CRPS的模型相比，训练计算量减少了10倍以上，与基于扩散的模型相比，推理延迟减少了10倍以上。U-Cast在不到12个H200 GPU天内完成训练，并在3秒内生成15天的集合预报。这些结果表明，可扩展的通用架构与高效的训练课程相结合，可以以极低的成本匹配复杂的领域特定设计，从而向更广泛的社区开放边界概率天气模型的训练。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
