发表机构
Department of Physics, University of Cambridge; ETH AI Center, ETH Zurich; Department of Applied Mathematics and Theoretical Physics, University of Cambridge（剑桥大学物理系; 苏黎世联邦理工学院人工智能中心; 剑桥大学应用数学与理论物理系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究比较四种概率机器学习天气预报模型与物理模型，发现它们虽能产生熟练预报，但常错误表示动能级联，且难以再现蝴蝶效应引起的小尺度集合扩散快速初始增长。
AI 中文摘要
本研究分析了四种最先进的概率机器学习天气预报（MLWP）模型中的动能（KE）谱、差动动能（DKE）谱以及跨空间尺度的KE传递特征，这些模型包括：NeuralGCM-ENS、FourCastNet 3、AIFS-ENS和GenCast。结果与基于物理的数值天气预报模型IFS-ENS的结果进行了比较。虽然NeuralGCM-ENS成功再现了预期的KE向上尺度传递，但其编码器阶段的噪声注入低估了中尺度KE。相反，AIFS-ENS、GenCast和FourCastNet 3产生了真实的KE谱幅度，但未能捕捉到预期的KE向上尺度传递。特别是，采用空间不相关随机扰动的AIFS-ENS和GenCast，在高波数处表现出KE的增强积累。所有被检查的模型都表现出向上尺度的误差增长，这反映在DKE谱峰随时间逐渐向更大波长移动。然而，MLWP模型难以再现与蝴蝶效应相关的小空间尺度上集合扩散的快速初始增长。结果表明，尽管MLWP模型能产生熟练的天气预报，但它们可能错误地表示已知的动能尺度传递。
英文摘要
This study analyses kinetic energy (KE) spectra, difference kinetic energy (DKE) spectra, and signatures of KE transfer across spatial scales in four state-of-the-art probabilistic machine learning weather prediction (MLWP) models: NeuralGCM-ENS, FourCastNet 3, AIFS-ENS, and GenCast. Results are compared with those from the physics-based numerical weather prediction model IFS-ENS. While NeuralGCM-ENS successfully reproduces the expected upscale transfer of KE, noise injection at its encoder stage underestimates mesoscale KE. Conversely, AIFS-ENS, GenCast, and FourCastNet 3 produce realistic KE spectral magnitudes but do not capture the expected upscale transfer of KE. In particular, AIFS-ENS and GenCast, which employ spatially uncorrelated stochastic perturbations, exhibit enhanced accumulation of KE at high wavenumbers. All examined models exhibit upscale error growth, reflected by the progressive shift of the DKE spectral peak toward larger wavelengths over time. However, the MLWP models struggle to reproduce the rapid initial growth of ensemble spread at small spatial scales associated with the butterfly effect. The results show that MLWP models can misrepresent the known scale transfer of kinetic energy despite producing skilful weather forecasts.
