发表机构
Boston University（波士顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对沿海海平面预测的AI扩散模型，发现其边际预测技能良好但联合空间结构差，该失效由变差函数分数检测，且是学习到的模拟器特有的结构不足问题。
AI 中文摘要
集成预测旨在采样结果的条件分布，但AI预测集成是否在联合意义上正确做到这一点仍未得到充分验证。我们针对美国东海岸8个潮汐观测站的次季节沿海海平面预测训练了一个扩散模型，海平面来自再分析数据，发现边际预测质量和联合预测质量存在解耦：每个站点和每个提前时效的边际技能均为正，而联合空间结构比气候学抽样更差。基于洗牌的置换分解显示，该失效对能量分数不可见，但被变差函数分数检测到。在0.7至170等效年范围内的Lorenz-96实验表明，无论训练量如何，该差距持续存在，且可由线性基线复现，这表明学习到的分布存在结构不足。动力集成未复现该失效，而确定性模拟器复现了该失效，说明该失效是学习到的模拟器特有的，而非集成预测普遍存在的问题。
英文摘要
Ensemble forecasting aims to sample the conditional distribution of outcomes; whether AI forecast ensembles do this correctly in a joint sense remains largely untested. We train a diffusion model for probabilistic subseasonal coastal sea level forecasts at eight US East Coast tide gauge stations, with sea level derived from reanalysis, and find that marginal and joint forecast quality decouple: positive skill at every station and lead time marginally, while joint spatial structure is worse than climatological draws. A shuffle-based permutation decomposition reveals this failure is invisible to the energy score but detected by the variogram score. Lorenz-96 experiments across 0.7-170 equivalent years show the gap persists regardless of training volume and is reproduced by a linear baseline, indicating structural inadequacy of the learned distribution. A dynamical ensemble does not replicate the failure while a deterministic emulator does, suggesting it is specific to learned emulators rather than ensemble forecasting generally.
