arXiv：cs.LG· Shan Zhao, Ilija Trajkovic, Julia Kaltenborn, Yaniv Gurwicz, Peer Nowack, David Rolnick, Julien Boussard·· 4 小时前AI 评分37
用分层因果表示学习建模气候模型中温度对强迫因子的响应
Learning Hierarchical Causal Representations of the Effects of Forcings on Temperature in Climate Models
AI 导读
研究者提出一种分层因果表示学习框架，应用于先进全球气候模型的海表温度场，显式建模内部气候变率引发的大气动力相互作用与温室气体、气溶胶浓度变化带来的强迫响应。在未见过的气候情景上评估时，该方法能准确预测全球平均及区域温度的长期演变，并对温室气体与气溶胶浓度扰动表现出物理上合理的响应。
正文
Abstract:Machine learning (ML) emulators provide a fast and cost-effective method to simulate climate change scenarios after being trained on Earth System Models projections. However, the black-box nature of those data-driven approaches limit the usability and trustworthiness of their outputs and in particular their use as causal attribution tools. Here, we develop a hierarchical causal representation learning framework applied to sea surface temperature fields from a state-of-the-art global climate model. As a key advance over previous work, our framework explicitly models both atmospheric dynamical interactions arising from internal climate variability and forced responses due to changes in atmospheric greenhouse gas and aerosol concentrations. When trained on future climate change scenarios, our method accurately predicts the long-term global mean and regional temperature evolution and shows physically realistic responses to perturbations in greenhouse gas and aerosol concentrations when evaluated on unseen scenarios. Our results underline the potential of causal representation learning frameworks for advancing climate model emulation.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2609.30995 [cs.LG] |
| (or arXiv:2609.30995v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.30995 arXiv-issued DOI via DataCite |
Submission history
From: Shan Zhao [view email]
[v1]
Fri, 25 Sep 2026 08:40:22 UTC (12,627 KB)
[v2]
Tue, 6 Oct 2026 15:00:35 UTC (12,627 KB)
来源：arXiv：cs.LG · arxiv.org