用因果学习提升北极海冰预测准确率
Correlation to Causation: A Causal Deep Learning Framework for Arctic Sea Ice Prediction
- 融合格兰杰因果与PCMCI+算法识别关键影响因素
- 在43年数据上提升预测精度并减少特征冗余
- 适合气候建模与高维动态系统预测研究者
传统机器学习依赖相关性，难以区分虚假关联与真实因果关系，限制了模型的鲁棒性、可解释性和泛化能力。为此，我们提出一种基于因果的深度学习框架，结合多变量格兰杰因果（MVGC）与PCMCI+因果发现算法，构建混合深度学习架构。利用1979至2021年共43年的每日和每月北极海冰范围（SIE）及海洋-大气数据集，该方法识别出具有因果显著性的关键因子，优先选择直接影响变量，降低特征维度，提升计算效率。实验表明，引入因果特征可显著提升模型在多个预报时长下的预测准确率与可解释性。该框架不仅适用于海冰预测，也为高维动态系统的可扩展预测建模提供了新思路，推动理论与应用双重进展。
原文摘要 · Abstract (English)
Traditional machine learning and deep learning techniques rely on correlation-based learning, often failing to distinguish spurious associations from true causal relationships, which limits robustness, interpretability, and generalizability. To address these challenges, we propose a causality-driven deep learning framework that integrates Multivariate Granger Causality (MVGC) and PCMCI+ causal discovery algorithms with a hybrid deep learning architecture. Using 43 years (1979-2021) of daily and monthly Arctic Sea Ice Extent (SIE) and ocean-atmospheric datasets, our approach identifies causally significant factors, prioritizes features with direct influence, reduces feature overhead, and improves computational efficiency. Experiments demonstrate that integrating causal features enhances the deep learning model's predictive accuracy and interpretability across multiple lead times. Beyond SIE prediction, the proposed framework offers a scalable solution for dynamic, high-dimensional systems, advancing both theoretical understanding and practical applications in predictive modeling.
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。