用扩散模型生成全球大气轨迹，1小时一次，0.25度精度
Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation
- 基于565M参数的潜在扩散模型，从观测数据推断大气状态
- 在ERA5数据上训练，可直接对任意观测条件进行轨迹重建
- 单模型实现再分析、滤波与预测，物理一致性高，无需重训练
深度学习推动了天气预报发展，但准确预测的前提是基于观测数据确定当前大气状态。本文提出Appa，一种基于得分的资料同化模型，可在0.25°分辨率下以1小时为间隔生成全球大气轨迹。该模型基于565M参数的潜在扩散模型，在ERA5数据上训练，能够对任意观测条件进行条件建模，无需重新训练。其概率框架统一实现了再分析、滤波与预报，从多种输入中生成物理一致的大气重构结果。实验表明，潜在得分基资料同化是未来全球大气建模系统的有力基础。
原文摘要 · Abstract (English)
Deep learning has advanced weather forecasting, but accurate predictions first require identifying the current state of the atmosphere from observational data. In this work, we introduce Appa, a score-based data assimilation model generating global atmospheric trajectories at 0.25\si{\degree} resolution and 1-hour intervals. Powered by a 565M-parameter latent diffusion model trained on ERA5, Appa can be conditioned on arbitrary observations to infer plausible trajectories, without retraining. Our probabilistic framework handles reanalysis, filtering, and forecasting, within a single model, producing physically consistent reconstructions from various inputs. Results establish latent score-based data assimilation as a promising foundation for future global atmospheric modeling systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。