Weather Emulators at the Frontier of Heat Extremes Predictability

AI 中文解读

天气预测迎来AI新玩家，但这次的结果有点出人意料。最新研究显示，多个顶尖AI模型——包括华为盘古、谷歌GraphCast等六个深度学习系统——在中期预报上已经能和传统物理模型打平甚至胜出，尤其擅长预测10到15天后的温度变化。听起来是场漂亮仗？不过细看有个大问题：AI模型预测极端高温时，总把热浪的峰值温度“打折”报，强度明显偏保守，而传统欧洲中期天气预报中心的IFS模型反而记得更准。原因在于AI预报有“磨皮”效应，像滤镜模糊了照片边缘，它对大气细节的还原度不够，更擅长给大趋势，不擅长捕捉极端峰值的尖锐程度。这对普通人意味着什么？往好了想，AI模型在中期温度预测上展现的速度和潜力，未来可能让天气预报更便宜、更新更频繁，尤其在预警热浪时会多一个参考工具。但现在还别指望它单独扛大梁——极端高温这种“致命一击”的预报，AI仍需补课。理想状态是AI跑速度、传统模型保精度，两者配合，才能让“提前两周知道要热死人”的预警更可靠。

Atmospheric predictability declines rapidly beyond the next ten days, such that forecasts at longer lead times primarily convey large-scale trends rather than specific states. Yet in a warming world, improving early warnings of extreme heat is an increasingly critical challenge. Here we evaluate six state-of-the-art deep learning weather emulators - Pangu-Weather, FuXi, ArchesWeather, AIFS, GraphCast and Aurora - alongside leading dynamical systems and statistical baselines in forecasting global near-surface temperature and extreme heat at lead times of 10-15 days. We find that several emulators rival or even surpass physics-based forecasts in deterministic temperature skill, but do so at the cost of reduced spectral fidelity, in a process widely known as blurring. While all models show some degree of predictive skill for extreme heat, most emulators under-represent peak intensities, and IFS recall is greater than that of any of the emulators. These results highlight both the emerging potential of AI to enhance extended range temperature prediction, and the remaining challenges in delivering reliable, actionable early warnings in a changing climate.