arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2607.05045physics.ao-ph
收藏

关于机器学习天气预报的谱系

On the Genealogy of Machine Learning Weather Prediction

Center for Western Weather and Water Extremes (CW3E)(西部天气与水极端中心);Scripps Institution of Oceanography(斯克里普斯海洋研究所);UC San Diego(加州大学圣地亚哥分校)

Mohammad Hassan Erfani

AI总结:

研究机器学习天气预报继承数值天气预报初值问题框架后的情况,对比‘科学替代建模’与‘自由形式数据驱动建模’两种传统,通过多种方式将建模范式映射到相关公式,指出模型选择需使架构和训练目标与物理或数据统计结构对齐。

摘要:

现代机器学习天气预报(MLWP)很大程度上继承了数值天气预报(NWP)的初值问题(IVP)框架。这种继承导致了学习自回归时间步长的主导范式,并限制了学习问题的定义和架构选择。本研究明确了这种继承关系,对比了两种哲学传统……我们得出结论,有原则的模型选择需要使架构和训练目标与物理系统结构或数据的统计结构明确对齐。

英文摘要:

Modern machine-learning weather prediction (MLWP) has largely inherited the initial-value-problem (IVP) framing of numerical weather prediction (NWP). This inheritance leads to a dominant paradigm of learned autoregressive time-stepping and constrains how the learning problem is defined and architectures are favored. In this study we make the inheritance explicit, contrast two philosophical traditions: "scientific surrogate modeling," where machine learning (ML) is embedded within a physical system and must respect its structural constraints, and "free-form data-driven modeling," where atmospheric fields are treated as spatiotemporal sequences and models learn latent dynamics without explicit physical constraints. By reviewing the governing primitive equations, surveying recent literature, and analyzing concrete physical examples, we map each modeling paradigm to either a state-conditioned or evolution operator formulation. We conclude that principled model selection requires explicitly aligning architecture and training objectives with either the physical system structure or the statistical structure of the data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑