用扩散模型实现并行生成连贯的天气预报集合，提升效率与精度。
Continuous Ensemble Weather Forecasting with Diffusion models
- 提出连续集合预报方法，无需自回归逐步生成，可完全并行采样。
- 在全局天气预报上达到竞争力水平，概率性评估表现良好。
- 兼容自回归推理，可在任意细粒度时间分辨率下保持准确率。
天气预报正从数值模拟转向数据驱动系统。早期研究聚焦于确定性预测，近期工作利用扩散模型生成高技能的集合预报。这些模型通常在单步预测上训练，并通过自回归方式逐步滚动推演。然而，该方法计算成本高，且在高时间分辨率下因累积步骤多而误差增大。本文提出连续集合预报（Continuous Ensemble Forecasting），一种新颖且灵活的扩散模型集合采样方法。该方法可完全并行生成时间一致的集合轨迹，无需自回归步骤。同时，该方法可与自回归推演结合，在任意精细时间分辨率下实现预报，且不牺牲准确性。实验表明，该方法在全局天气预报任务中表现优异，具备良好的概率性特性。
原文摘要 · Abstract (English)
Weather forecasting has seen a shift in methods from numerical simulations to data-driven systems. While initial research in the area focused on deterministic forecasting, recent works have used diffusion models to produce skillful ensemble forecasts. These models are trained on a single forecasting step and rolled out autoregressively. However, they are computationally expensive and accumulate errors for high temporal resolution due to the many rollout steps. We address these limitations with Continuous Ensemble Forecasting, a novel and flexible method for sampling ensemble forecasts in diffusion models. The method can generate temporally consistent ensemble trajectories completely in parallel, with no autoregressive steps. Continuous Ensemble Forecasting can also be combined with autoregressive rollouts to yield forecasts at an arbitrary fine temporal resolution without sacrificing accuracy. We demonstrate that the method achieves competitive results for global weather forecasting with good probabilistic properties.
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。