机器学习找到更优初始条件，让天气预报突破两周极限，30天仍有效。
Atmospheric Predictability Beyond 30 Days with Machine Learning
- 用机器学习优化初始条件，提升长期预报精度
- 10天误差降低86%，30天后仍保持预报能力
- 适合关注气象预报突破与机器学习应用的研究者
大气可预报性研究长期认为，小尺度误差快速增长导致确定性天气预报的内在极限约为两周。本文通过图神经网络模型GraphCast，对2020年双日预报进行初始条件优化，相比再分析数据提供的控制预报，10天平均误差降低86%，预报技能持续超过30天。最优初始条件的平均扰动显示，大尺度、空间相干的修正主要反映哈德利环流的增强。使用GraphCast优化的初始条件在Pangu-Weather模型中实现21%的误差降低，峰值出现在第4天，表明这些分析修正同时针对模型和分析误差。结果证明，存在能产生远超两周的确定性预报技能的初始条件。能否实时识别此类条件以改进业务预报，仍是未来研究方向。
原文摘要 · Abstract (English)
Atmospheric predictability research has long held that rapid error growth at small spatial scales imposes an intrinsic limit of roughly two weeks on deterministic weather forecast skill. We challenge this limit using GraphCast, a machine-learning weather model, by optimizing initial conditions for twice-daily forecasts spanning 2020. This approach yields an average error reduction of 86% at ten days relative to control forecasts from reanalysis initial conditions, with skill lasting beyond 30 days. Mean optimal initial-condition perturbations reveal large-scale, spatially coherent corrections primarily reflecting an intensification of the Hadley circulation. Forecasts using GraphCast-optimal initial conditions in the Pangu-Weather model achieve a 21% error reduction, peaking at four days, indicating that analysis corrections reflect adjustments that target both model and analysis error. These results demonstrate the existence of initial conditions producing skillful deterministic forecasts far beyond two weeks. Whether such initial conditions can be identified in real-time for improving operational weather forecasts remains a topic of future research.
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。