Chronos-2 论文提出面向多变量时序预测的基础模型
Chronos-2: A foundation model for multivariate time series forecasting
研究者发布 Chronos-2 论文，提出一个可零样本预测的时序基础模型，能建模多变量时间序列与异构协变量之间的交互并生成概率预测。基准上相对最强基线平均提升 skill score 5.2 个百分点，胜率提升 10 个百分点；单块中端 GPU 不到一秒可完成 100 条序列预测，端到端比最佳任务专用点预测和概率预测方法分别快 50 倍和 1000 倍。
Authors:Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer, Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella, Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo Guerron, Florian Saupe, Markus Reichstein, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang, Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider
Abstract:Accurate forecasting with uncertainty quantification is critical in a variety of scientific applications ranging from epidemiology and economics to energy systems and earth sciences. Yet most forecasting models still need to be developed and trained separately for each domain-specific dataset. Time series foundation models (TSFMs) aim to remove this limitation and enable the application of the same model across domains through large-scale pretraining. However, most existing TSFMs treat each time series independently and therefore cannot model interactions among time series and external drivers. Here, we introduce Chronos-2, a foundation model for zero-shot forecasting that models the interactions between multivariate time series and heterogeneous covariates, which commonly arise in scientific applications. The model infers relationships among time series directly from historical context and generates probabilistic forecasts without task-specific treatment. Across various benchmarks, Chronos-2 achieves state-of-the-art accuracy on average by improving skill scores by 5.2 percentage points relative to the strongest baselines and increasing win rates by 10 percentage points. Chronos-2 is also computationally efficient, generating forecasts for 100 time series in under one second on a single mid-range GPU, 50x and 1000x faster end-to-end than the best task-specific point and probabilistic forecasters, respectively. In addition, we demonstrate its effectiveness in diverse scientific settings -- including infectious-disease forecasting, macroeconomic modeling, carbon-flux prediction, and runoff simulation -- where the model matches or surpasses specialized methods developed for each domain. These results show that a single pretrained model can capture structure shared across temporal systems.
| Comments: | 41 pages, 9 figures. Extended version of the Chronos-2 technical report (arXiv:2510.15821), adding scientific case studies (epidemiology, macroeconomics, carbon flux, hydrology, hierarchical forecasting), additional baselines, ablation studies, and calibration analysis. Code: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML) |
| Cite as: | arXiv:2610.41956 [cs.LG] |
| (or arXiv:2610.41956v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41956 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Abdul Fatir Ansari [view email]
[v1]
Fri, 30 Oct 2026 16:08:23 UTC (1,919 KB)
来源：arXiv cs.AI · arxiv.org