用于全球天气预报的时间步条件Transformer
Timestep-Conditioned Transformers for Global Weather Forecasting
浏览论文内容
中文总结 AI 辅助
该研究提出名为GEM-3的轻量级邻域注意力Transformer，通过显式多时间步推理解决天气预报时间步长的权衡问题，实现平衡可预测性与可用性的全球天气预报系统。
中文摘要 AI 辅助
现有的机器学习天气预报模型依赖于预先确定的固定自回归时间步长。模型时间步长的选择涉及一个基本权衡：较短的时间步长（例如1至6小时）能精细解析日周期内的大气动态，但在给定预报 horizon 下会增加误差累积；而较长的时间步长（例如24小时）减少误差累积，但限制了短程预报的可用性，而短程预报具有高次日可预测性。本研究中，我们提出GEM-3，这是一种概率全球天气模型，通过显式多时间步推理解决上述权衡问题。该模型仅需一组训练权重，即可在推理时配置模型时间步长，以在广泛的预报范围内平衡可预测性与可用性。此外，我们发现混合时间步长训练相比时间步长专用模型，能持续提升滚动稳定性。GEM-3本质上是一种轻量级邻域注意力Transformer，在等距网格上具有约1.34亿参数，相比其前身GEM-2具备多项架构改进。最终形成的实用预报系统兼具接近当前最优（near-SOTA）的中程概率技能、稳定的扩展程滚动、高效的训练与推理，以及与决策相关的诊断功能。
英文摘要
Existing machine-learning weather forecasting models rely on predetermined and fixed autoregressive timesteps. The choice of model timestep involves a fundamental trade-off: shorter timesteps (e.g. 1 to 6 hours) finely resolve atmospheric dynamics within the diurnal cycle but increase error accumulation for a given forecast horizon, while longer timesteps (e.g. 24 hours) reduce error accumulation but limit the usability of short-range forecasts where sub-daily predictability is high. In this work, we present GEM-3, a probabilistic global weather model that addresses this trade-off through explicit multi-timestep inference. With a single set of trained weights, the model timestep can be configured at inference time to balance predictability and usability across a broad forecast horizon. Additionally, we find that mixed-timestep training consistently improves rollout stability relative to timestep-specialist models. Under the hood, GEM-3 is a lightweight neighborhood-attention transformer with ~134M parameters on an equirectangular grid with a number of architectural advancements beyond its predecessor GEM-2. The result is a practical forecasting system that couples near-SOTA medium-range probabilistic skill, stable extended-range rollouts, efficient training and inference, and decision-relevant diagnostics.
