深度学习气候模型成功模拟了未训练时期的极端天气，表现媲美传统模型。
Deep Learning Atmospheric Models Reliably Simulate Out-of-Sample Land Heat and Cold Wave Frequencies
- 用深度学习结合物理规律的混合模型和纯数据驱动模型进行气候推演。
- 在1900-1960年间，两类模型对热浪与寒潮频率的模拟与真实情况基本吻合。
- 混合模型更接近真实气候持续性，适合研究极端事件的长期变化。
基于深度学习的全球环流模型（GCM）正成为快速气候模拟的新工具，但其在训练范围外模拟极端事件的能力尚不明确。本文评估了两种模型——混合型神经全球环流模型（NGCM）和纯数据驱动的深度学习地球系统模型（DL\textit{ESy}M）——与传统高分辨率陆气模型（HiRAM）在模拟陆地热浪与寒潮方面的表现。所有模型均以1900–2020年观测海表温度和海冰为强迫，聚焦于未训练的早期20世纪时期（1900–1960）。结果显示，两类深度学习模型在未见气候条件下仍具备良好泛化能力，其热浪与寒潮事件的频率及空间分布模式与HiRAM相当，整体性能相近。仅在北亚与北美部分地区，三者在1940–1960年间均表现不佳。由于温度自相关过强，DL\textit{ESy}M倾向于高估极端事件频率；而物理-深度学习混合的NGCM则表现出更接近HiRAM的持续性特征。
原文摘要 · Abstract (English)
Deep learning (DL)-based general circulation models (GCMs) are emerging as fast simulators, yet their ability to replicate extreme events outside their training range remains unknown. Here, we evaluate two such models -- the hybrid Neural General Circulation Model (NGCM) and purely data-driven Deep Learning Earth System Model (DL\textit{ESy}M) -- against a conventional high-resolution land-atmosphere model (HiRAM) in simulating land heatwaves and coldwaves. All models are forced with observed sea surface temperatures and sea ice over 1900-2020, focusing on the out-of-sample early-20th-century period (1900-1960). Both DL models generalize successfully to unseen climate conditions, broadly reproducing the frequency and spatial patterns of heatwave and cold wave events during 1900-1960 with skill comparable to HiRAM. An exception is over portions of North Asia and North America, where all models perform poorly during 1940-1960. Due to excessive temperature autocorrelation, DL\textit{ESy}M tends to overestimate heatwave and cold wave frequencies, whereas the physics-DL hybrid NGCM exhibits persistence more similar to HiRAM.
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。