Sonny：突破中范围天气预报的计算壁垒
Sonny: Breaking the Compute Wall in Medium-Range Weather Forecasting
- Department of Computer Science and Engineering, Sejong University（信息科学与工程系，世宗大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
Sonny提出一种高效层级变压器模型，在合理计算预算内实现与操作系统竞争的中范围预报性能，通过两阶段StepsNet设计和EMA训练策略，在WeatherBench2上展现稳健的预报能力。
AI中文摘要：
天气预报是保护生命和基础设施免受高影响大气事件影响的基本问题。近年来，基于深度学习的数据驱动天气预报方法已展现出强大的性能，通常达到与操作数值系统相媲美的准确水平。然而，许多现有模型依赖于大规模训练制度和计算密集型架构，这为计算资源有限的学术团体提出了实际障碍。本文介绍了一个高效的分层变压器Sonny，它在合理的计算预算内实现了具有竞争力的中范围预报性能。Sonny的核心是一种两阶段StepsNet设计：狭窄的慢路径首先建模大规模大气动力学，随后的全宽快路径整合热力学相互作用。为了在不额外进行微调阶段的情况下稳定中范围滚动，我们在训练期间应用指数移动平均（EMA）。在WeatherBench2上，Sonny展现出稳健的中范围预报能力，与操作基线相媲美，并在延长的热带预报时间上明显优于FastNet。在实践中，Sonny可以在约5.5天内在一个NVIDIA A40 GPU上训练到收敛。
英文摘要：
Weather forecasting is a fundamental problem for protecting lives and infrastructure from high-impact atmospheric events. Recently, data-driven weather forecasting methods based on deep learning have demonstrated strong performance, often reaching accuracy levels competitive with operational numerical systems. However, many existing models rely on large-scale training regimes and compute-intensive architectures, which raises the practical barrier for academic groups with limited compute resources. Here we introduce Sonny, an efficient hierarchical transformer that achieves competitive medium-range forecasting performance while remaining feasible within reasonable compute budgets. At the core of Sonny is a two-stage StepsNet design: a narrow slow path first models large-scale atmospheric dynamics, and a subsequent full-width fast path integrates thermodynamic interactions. To stabilize medium-range rollout without an additional fine-tuning stage, we apply exponential moving average (EMA) during training. On WeatherBench2, Sonny yields robust medium-range forecast skill, remains competitive with operational baselines, and demonstrates clear advantages over FastNet, particularly at extended tropical lead times. In practice, Sonny can be trained to convergence on a single NVIDIA A40 GPU in approximately 5.5 days.
