发表机构
National University of Singapore（新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
S2S-JEPA将JEPA范式引入次季节到季节预报，通过预测缓慢变化分量，在5-6周达到与ECMWF相当并部分超越的技巧。
AI 中文摘要
次季节到季节（S2S）时间尺度，大致为未来两周到两个月，是农业、能源和水资源管理等行业的关键预报窗口。然而，它被广泛称为“可预测性荒漠”。近期的人工智能天气模型在两周内的预报表现出色，但超过两周后性能下降，这主要是因为它们被训练用于预测精细尺度的细节，而这些细节在S2S时间尺度上既不可预测也不必要。我们认为，一个更具物理基础的目标是仅预报那些保持可预测性的缓慢变化分量。计算机视觉领域通过联合嵌入预测架构（JEPA）得出了相同的结论，该架构在潜在空间中预测，丢弃不可预测的细节。在这项工作中，我们引入了S2S-JEPA，将JEPA范式应用于S2S预报。它通过借鉴最先进的人工智能天气模型的设计元素，针对这一任务进行了定制。S2S-JEPA达到了与黄金标准的ECMWF基于物理的集合预报相当的技巧，并在第5至第6周的多项指标上超越了它。
英文摘要
The subseasonal-to-seasonal (S2S) timescale, roughly from two weeks to two months ahead, is a critical forecast window for sectors such as agriculture, energy, and water management. Yet, it is widely known as the `predictability desert'. Recent AI weather models excel up to two weeks ahead but deteriorate beyond, largely because they are trained to predict fine-scale details that are neither predictable nor essential at S2S timescales. We argue that a more physically grounded objective is to forecast only the slowly varying components that remain predictable. Computer vision reached the same conclusion with the Joint-Embedding Predictive Architecture (JEPA), which predicts in latent space, discarding unpredictable details. In this work, we introduce S2S-JEPA, which brings the JEPA paradigm to S2S forecasting. It is tailored to this task through design elements from state-of-the-art AI weather models. S2S-JEPA achieves comparable skill to the gold-standard ECMWF physics-based ensemble and surpasses it on multiple metrics at weeks 5 to 6.
