analiza aiqbench
The paper presents Chronos-2, a time series foundation model that forecasts multiple related series and external covariates jointly, rather than treating each series independently. The authors report state-of-the-art average accuracy on benchmarks and large speedups over task-specific forecasters, though these results are self-reported and should be checked against independent evaluations. For readers, the key questions are whether the zero-shot gains hold on real, out-of-distribution scientific data and how the joint modelling of covariates compares with simpler baselines.
Chronos-2: A foundation model for multivariate time series forecasting
arXiv:2610.41956v1 Announce Type: new 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.
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.
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
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
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)
Text integral sub licența deschisă a publicației · 353 cuvinte
Subiecte conexe
StationPDE: Station-Oriented Surface PDE Learning for Multi-Station Multivariate Weather Forecasting
arXiv · 22 sept. 2026
Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting
arXiv · 16 iun. 2026
QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting
arXiv · 7 oct. 2026
CoRe: Coherence and Relational Alignment for Multivariate Time Series Forecasting
arXiv · 18 sept. 2026