基于分层多尺度建模，提升混沌系统长期预测精度。
ChaosNexus: A Foundation Model for ODE-based Chaotic System Forecasting with Hierarchical Multi-scale Awareness
- 采用分层时间块处理，捕捉长程依赖与高频波动
- 在9000个合成系统上实现更优吸引子统计精度，5天天气预报零样本误差低于1℃
- 融合专家混合与频谱指纹，适配不同混沌系统
基础模型在通过大规模预训练实现基于常微分方程的混沌系统零样本或少样本预测方面展现出巨大潜力。然而，现有架构往往难以捕捉混沌动力学的多尺度时间结构和显著的频谱特征。为此，我们提出ChaosNexus，一种基于新型ScaleFormer架构的混沌系统预测基础模型。该模型通过处理分层变化的时间块，有效捕捉长程依赖并保留高频波动。为应对不同系统间的异质性，我们在每个ScaleFormer模块中集成专家混合（MoE）层，并显式将最终预测条件于学习到的频率指纹，提供系统全局频谱视图。在超过9000个合成系统的广泛评估中，ChaosNexus在长期吸引子统计上达到更优保真度，同时保持竞争性的点对点准确率。此外，在真实世界应用中，其在5天站级天气预测中实现低于1℃的惊人零样本平均误差。代码已开源：https://github.com/TomXaxaxa/ChaosNexus。
原文摘要 · Abstract (English)
Foundation models have shown great promise in achieving zero-shot or few-shot forecasting for ODE-based chaotic systems via large-scale pretraining. However, existing architectures often fail to capture the multi-scale temporal structures and distinct spectral characteristics of chaotic dynamics. To address this, we introduce ChaosNexus, a foundation model for chaotic system forecasting underpinned by the proposed ScaleFormer architecture. By processing temporal contexts across hierarchically varying patch sizes, ChaosNexus effectively captures long-range dependencies and preserves high-frequency fluctuations. To address heterogeneity across distinct systems, we integrate Mixture-of-Experts (MoE) layers into each ScaleFormer block and explicitly condition the final forecasts on a learned frequency fingerprint, providing the model with a global spectral view of the system. Extensive evaluations on over 9,000 synthetic systems demonstrate that ChaosNexus achieves superior fidelity in long-term attractor statistics while maintaining competitive point-wise accuracy. Furthermore, in real-world applications, it achieves a remarkable zero-shot mean error below 1°C for 5-day station-based weather forecasting. Codes are available at https://github.com/TomXaxaxa/ChaosNexus.
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。