发表机构
University of California Irvine; San Diego State University; University of Oklahoma; NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography（加州大学尔湾分校; 圣地亚哥州立大学; 俄克拉荷马大学; NSF可信AI天气、气候与海岸海洋研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究探讨扩散模型作为递归环境预报的稳定机制，发现其能抑制误差增长，但实际效益取决于预测信息的可用性。
AI 中文摘要
在环境预报中，延长预报提前期同时保持预测技能仍然是一个重大挑战。我们研究了基于扩散的展开作为递归预报的稳定机制，使用了低维水位时间序列和高维降水场。在这两种模态中，扩散抑制了递归误差增长，最大的稳定效果出现在确定性展开最不稳定的地方。然而，稳定并不保证预报保真度。在水位实验中，随着展开失去外部预测信息的访问，预报逐渐失去事件级保真度，轨迹级比较显示扩散可以在保持数值稳定的同时向中心值收缩并表现出减少的变异性。在降水实验中，整个展开过程中保留了来自数值天气预报的条件约束，扩散更好地保持了空间组织和事件检测技能。综合这些对比实验表明，扩散可以控制递归误差放大，而其实际效益还取决于可用于约束未来演化的预测信息。
英文摘要
Extending forecast lead times while maintaining predictive skill remains a major challenge in environmental forecasting. We investigate diffusion-based rollouts as a stabilization mechanism for recursive forecasting using low-dimensional water-level time series and high-dimensional precipitation fields. Across both modalities, diffusion suppresses recursive error growth, with the largest stabilization occurring where deterministic rollouts are most unstable. However, stabilization does not guarantee forecast fidelity. In the water-level experiments, forecasts progressively lose event-level fidelity as the rollout loses access to external predictive information, and trajectory-level comparisons show that diffusion can remain numerically stable while contracting toward central values and exhibiting reduced variability. In the precipitation experiments, which retain conditioning from numerical weather prediction throughout the rollout, diffusion better preserves spatial organization and event-detection skill. Together, these contrasting experiments indicate that diffusion can control recursive error amplification, while its practical benefit also depends on the predictive information available to constrain future evolution.
