融合外部信号提升水文时间序列预测精度
Leveraging Exogenous Signals for Hydrology Time Series Forecasting
- 引入自然年周期等外部时序信号增强模型输入
- 在671个站点上显著优于基础模型和有限输入模型
- 适合水文建模与气候相关研究者参考
近期时间序列研究推动了基础模型的发展，但多数先进时间序列基础模型尚未在物理科学的具体下游任务中得到验证。本文探究将领域知识融入时间序列模型对水文降雨-径流建模的作用。基于包含671个站点、六类时间序列流及30个静态特征的CAMELS-US数据集，对比了基线模型与基础模型的表现。结果表明，整合全面已知外部输入的模型显著优于输入受限的模型，包括部分基础模型。尤其值得注意的是，引入自然年周期时间序列带来最显著的性能提升。
原文摘要 · Abstract (English)
Recent advances in time series research facilitate the development of foundation models. While many state-of-the-art time series foundation models have been introduced, few studies examine their effectiveness in specific downstream applications in physical science. This work investigates the role of integrating domain knowledge into time series models for hydrological rainfall-runoff modeling. Using the CAMELS-US dataset, which includes rainfall and runoff data from 671 locations with six time series streams and 30 static features, we compare baseline and foundation models. Results demonstrate that models incorporating comprehensive known exogenous inputs outperform more limited approaches, including foundation models. Notably, incorporating natural annual periodic time series contribute the most significant improvements.
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。