독서리서치레이더투자 프레임워크
로그인 / 회원가입
← 읽기로 돌아가기
뉴스주제 · AI气候模型极端预测중대3 분 소요DisconfirmAI 편집부

Oxford Professor Philip Stier: AI Models Face Fundamental Difficulties in Predicting Out-of-Distribution Extreme Events

Philip Stier, Professor of Atmospheric Physics at the University of Oxford and Director of the Intelligent Earth Centre, explains on a Man Group podcast why AI climate models struggle to predict extreme events that have never appeared in their training data, and how biases in reanalysis data combined with large-sample ensembles can create a false sense of precision.

2026-10-22 06:00 GMT+8

At the University of Oxford, Professor of Atmospheric Physics and Director of the Intelligent Earth Centre, Philip Stier, discussed with Jason Mitchell, Chief Investment Officer for Responsible Investment at Man Group, how artificial intelligence is transforming climate modeling during an episode of the firm's "A Sustainable Future" podcast. Stier’s core assessment is that purely data-driven AI models face fundamental difficulties when predicting out-of-distribution extreme events, a limitation that cannot be overcome simply by increasing the volume of training data or running more simulations.

Stier defines the challenge of predicting climate change as an "out-of-distribution problem": we are required to forecast states that have never occurred in the training dataset. Traditional physical models encode physical laws through systems of equations; these equations remain valid even under unprecedented conditions. In contrast, AI models learn patterns from historical observations. When future states exceed the coverage of the training data, the model lacks a basis for extrapolation. He cites the current El Niño event as an example: because observational records are too short, such extreme ENSO (El Niño-Southern Oscillation) events may not be present in the training data, making pure AI-driven climate predictions unreliable in such scenarios.

A deeper issue lies in the biases inherent in the training data itself. Stier points out that most AI weather models currently rely on reanalysis data for training—a combination of historical observations and outputs from traditional physical models. This means AI inherits not only the flaws of observational data (such as insufficient coverage in developing countries and limited funding for public observation systems) but also the parametrization biases of the physical models themselves. For instance, reanalysis data does not idealize the diurnal cycle of precipitation, which is related to the parametrization of convective clouds; AI models will learn this same bias. While acceptable for short-term weather forecasting provided predictive skill improves, this inherited bias can distort judgments on key processes like cloud feedback in climate prediction.

로그인 / 회원가입
독서리서치레이더투자 프레임워크

Stier’s warnings regarding the misleading effects of large-sample ensembles are particularly specific. He notes that running "very, very large" ensembles creates a false sense of certainty—results are often reported to high decimal precision—but this does not mean true uncertainty has been reduced. If the model itself contains biases affecting the tail distribution, then even perfect sampling of the model’s tail yields incorrect estimates of extreme events. He mentions that academia is researching methods to guide generative models to efficiently sample rare tails, but emphasizes that these approaches are only meaningful if the underlying model is reliable and well-calibrated.

For practitioners using AI-assisted investment research, Stier’s argument provides a clear boundary for validation: when the prediction target involves out-of-distribution events, the model’s output should not be assigned the same confidence level as in-distribution predictions. Similar situations in financial markets include unprecedented liquidity crises, tail risks of new asset classes, or market behavior following structural breaks. Precise probabilities generated by large-sample Monte Carlo simulations or backtesting are themselves misleading if the underlying model fails to capture critical mechanisms. Stier believes the pragmatic path to resolving this issue is to combine physical constraints with data-driven methods, rather than using AI to completely replace equation-based modeling.

출처

  • man.com↗
주제

AI气候模型极端预测

【背景】随着AI气象模型(如FourCastNet, GraphCast)在短期天气预报中超越传统物理模型,学界开始担忧其在长期气候预测中的可靠性。核心争议在于分布外(Out-of-Distribution, OOD)泛化能力:AI能否准确…

5 단계1 건업데이트됨 2026-11-17 00:30

현재까지의 과정

  1. 2026-07-03牛津气候研究网络(OCRN)举办研讨会,Philip Stier主持,讨论AI在气候预测中的机遇与危险,强调AI与物理模型协作而非替代。climate.ox.ac.uk ↗
  2. 2026-08-27牛津大学发布上述研讨会回顾文章,指出AI在长周期、非平稳气候条件下的可解释性和鲁棒性挑战。climate.ox.ac.uk ↗
  3. 2026-10-05Man Group播客录制,Philip Stier详细阐述AI模型在分布外极端事件预测上的根本困难及数据偏差问题。man.com ↗

아직 해결되지 않은 문제

  • 如何建立标准化的分布外(OOD)评估协议,以区分模型的真实预测能力与过拟合现象?
  • 生成式AI模型(如扩散模型)在模拟极端事件尾部统计特征时,是否能在计算效率与物理一致性之间取得平衡?
  • 金融机构在利用AI进行气候风险定价时,应如何量化并调整因模型OOD失效导致的潜在低估风险?
전체 주제 읽기 →
리서치 계속하기 →