发表机构
University of Chicago; Nanjing University; New York University（芝加哥大学; 南京大学; 纽约大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对AI气象预测模型，发现其预测精度源于训练数据粗粒化，回溯预测精度低于前向预测且缺失蝴蝶效应，减少粗粒化可提升物理性但降低精度，为相关理论与气候模拟提供新视角。
AI 中文摘要
AI气象预测（AIWP）模型可与基于物理的模型相媲美，但其意外预测精度的来源以及物理保真度仍不明确。本研究在涵盖基于观测的再分析、通用环流模型及多尺度洛伦兹系统的层级范围内开展研究，结果表明，AI模型可被训练以精准预测过去（回溯预测），尽管回溯预测的精度系统性低于前向预测。然而，精准的回溯预测似乎违反了热力学第二定律，且所有这些预测与回溯预测模型均错失了蝴蝶效应。研究将令人惊讶的预测精度、缺失的蝴蝶效应及精准的回溯追溯至单一原因：训练数据不可避免的粗粒化，其消除了快速小尺度和/或某些变量。从洛伦兹系统到官方Pangu-Weather模型，减少粗粒化可使AI预测更具物理性（时间之箭与类蝴蝶效应显现），但预测精度会下降。研究结果为AIWP模型的预测技能提供了一种解释：与基于物理的模型不同，它们隐含学习快速小尺度如何影响大尺度，却未继承其快速误差增长。更广泛的意义在于，AI模型的大量出现要求重新审视可预测性理论与长期气候模拟策略，且回溯预测为此类分析提供了一个有用的新视角。
英文摘要
AI weather prediction (AIWP) models rival physics-based models, yet the sources of their unexpected forecast accuracy and the degree of their physical fidelity remain unclear. Here, across a hierarchy spanning observation-based reanalysis, a general circulation model, and the multi-scale Lorenz system, we show that AI models can be trained to skillfully predict the past (backcast), though backcasts are systematically less accurate than forecasts. However, skillful backcasting appears to violate the second law of thermodynamics, and all these forecasting and backcasting models miss the butterfly effect. We trace the surprising forecast accuracy, missing butterfly, and skillful backcasting to a single cause: inevitable coarse-graining of training data, which removes fast, small scales and/or some variables. From the Lorenz system to official Pangu-Weather models, reducing coarse-graining makes AI predictions more physics-like (arrow of time and butterfly-like effects emerge), but forecast accuracy declines. Results offer an explanation for AIWP models' forecast skill: unlike physics-based models, they implicitly learn how fast, small scales affect large scales without inheriting their rapid error growth. Broader implications are that AI models' proliferation calls for revisiting predictability theories and long-term climate emulation strategies, and backcasting offers a useful, new lens for such analyses.
