arXiv：cs.LG· Tom Beucler, J. David Neelin, Hui Su, Shivanshi Asthana, Chris Bretherton, Will Chapman, Costa Christopoulos, Spencer K. Clark, Aditya Grover, Ignacio Lopez-Gomez, Tapio Schneider, Adam Subel, Oliver Watt-Meyer·· 4 小时前AI 评分37
从天气到气候：人工智能的路径
Artificial intelligence pathways from weather to climate
AI 导读
一篇综述指出，基于大气再分析数据训练的自回归模型在临近、中期和次季节至季节尺度上已媲美动力模式，并能以更低成本生成校准良好的集合预报。作者提出 AI 气候建模的两项最低要求：外部强迫因子须显式进入以支持独立变化干预，且须在包含极端与反事实轨迹的分布外条件下做鲁棒性压力测试。通过只推进目标变量、采用更长步长，AI 可比 GPU 移植的动力模式缩短求解时间，AI 降尺度策略则部分替代显式精细分辨率。
正文
Authors:Tom Beucler, J. David Neelin, Hui Su, Shivanshi Asthana, Chris Bretherton, Will Chapman, Costa Christopoulos, Spencer K. Clark, Aditya Grover, Ignacio Lopez-Gomez, Tapio Schneider, Adam Subel, Oliver Watt-Meyer
Abstract:Deep learning has made rapid advances in weather forecasting: autoregressive models trained on atmospheric reanalyses now rival dynamical models across nowcasting, medium-range, and subseasonal-to-seasonal lead times, producing well-calibrated ensemble forecasts at reduced cost. We review these advances and consider their extension to climate horizons, where the challenge shifts from initial-condition skill to producing reliable statistical responses under altered forcings. AI-powered climate prediction systems must produce credible forced responses to drivers (e.g., greenhouse gases, land-use change) typically outside the observed record. We propose two minimum requirements for AI in climate modeling: (i) external forcing agents must enter explicitly enough to support interventions in which they vary independently; and (ii) robustness must be stress-tested in out-of-distribution regimes, including extremes and counterfactual trajectories. Using leading AI autoregressive emulators and hybrid physics-AI models, we identify development and coupling challenges. Comparing the reported throughput of these models with that of GPU-ported dynamical models highlights how AI can reduce time-to-solution by advancing only the target variables at the required resolution and using longer time steps, rather than integrating a full high-frequency, multivariate state. Diverse AI downscaling strategies can partially substitute for explicit fine-scale resolution, paving the way toward inexpensive local hazard assessment across prediction horizons.
| Comments: | 33 pages, 10 figures. Submitted to "Science Advances" |
| Subjects: | Atmospheric and Oceanic Physics (physics.ao-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.09770 [physics.ao-ph] |
| (or arXiv:2610.09770v1 [physics.ao-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09770 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tom Beucler [view email]
[v1]
Wed, 7 Oct 2026 09:52:47 UTC (17,389 KB)
来源：arXiv：cs.LG · arxiv.org