检验机器学习气候模型在气候变化中的泛化能力
Do machine learning climate models work in changing climate dynamics?
- 用分布外评估方法测试机器学习模型在气候数据中的表现
- 不同场景下模型性能差异显著，泛化能力普遍不足
- 为气候风险预测提供可靠应用的实用建议
气候变化正加速极端事件的频率和严重程度，使其偏离既定模式。预测这些分布外（OOD）事件对评估风险和指导气候适应至关重要。尽管机器学习（ML）模型在提供精确、高速气候预测方面展现出潜力，但其在分布变化下的泛化能力仍是重大局限，且在气候领域尚未得到充分探索。本研究通过将成熟的分布外评估方法适配到气候数据，系统评估了最先进的基于机器学习的气候模型在多种分布外情景下的表现。大规模数据集实验揭示了不同场景下性能的显著波动，揭示了现有模型的优势与局限。研究结果强调了构建稳健评估框架的重要性，并为机器学习在气候风险预测中的可靠应用提供了可操作的洞见。
原文摘要 · Abstract (English)
Climate change is accelerating the frequency and severity of unprecedented events, deviating from established patterns. Predicting these out-of-distribution (OOD) events is critical for assessing risks and guiding climate adaptation. While machine learning (ML) models have shown promise in providing precise, high-speed climate predictions, their ability to generalize under distribution shifts remains a significant limitation that has been underexplored in climate contexts. This research systematically evaluates state-of-the-art ML-based climate models in diverse OOD scenarios by adapting established OOD evaluation methodologies to climate data. Experiments on large-scale datasets reveal notable performance variability across scenarios, shedding light on the strengths and limitations of current models. These findings underscore the importance of robust evaluation frameworks and provide actionable insights to guide the reliable application of ML for climate risk forecasting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。