AI天气模型能否超两周预测？研究揭示长期预报失败的三类根源。
Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts
- 通过一年滚动实验，将长期预报失败分为三类：爆炸、漂移和季节性丧失。
- 稳定模型能抑制高频噪声，不依赖随机输入也能生成独特气象轨迹。
- 适用于关注长时序天气建模的气象学家与AI模型开发者。
尽管人工智能天气模型在短中期预测（至15天）表现优异，但在长期滚动预测中常出现未明确定义的“不稳定性”。本文通过九个前沿AI天气模型的一年滚动实验，首次系统分类此类失败为三类：爆炸、漂移与季节性丧失。分析表明，稳定性取决于对小时空尺度的处理：不稳定模型会放大高频能量，而稳定模型则具备去噪能力。即使输入加噪，稳定模型仍能生成由初始状态决定的独特天气路径。通过基于视觉变换器（ViT）架构的消融实验，验证了模型结构设计对稳定性的影响。
原文摘要 · Abstract (English)
While AI weather models excel at short-to-medium range forecasts (up to 15 days), they frequently suffer from ill-defined "instabilities" when rolled out over longer horizons. This work addresses the lack of a formal taxonomy by categorizing these failures into three distinct regimes: blow-up, drift, and loss of seasonality, through year-long rollouts of nine state-of-the-art AI weather models. Our analysis reveals that stability hinges on the treatment of small spatio-temporal scales: unstable models amplify high-frequency energy, while stable models act as denoisers when noise is added to their inputs. Far from reducing these models to mere stochastic parrots, our findings highlight that stable models generate unique weather trajectories, conditioned on the initial state. We verify our findings through ablation studies on architectural design choices, conducted using state-of-the-art Vision Transformer (ViT) AI weather model architectures.
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。