aiqbench analysis
AdaWeather introduces an adaptive framework that combines probabilistic weather forecasts using machine learning and mixture of experts to achieve robust, unified predictions. Theoretically, it improves upon traditional methods by establishing logarithmic regret bounds relative to the best static mixture of experts in hindsight. Empirically, the approach demonstrates measurable improvements in temperature forecasting, addressing the challenge where no single model consistently dominates across varying spatiotemporal contexts.
AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret
arXiv:2606.02663v1 Announce Type: cross Abstract: Recent advances in machine learning have produced probabilistic weather forecasting models comparable to state-of-the-art numerical weather predictors. But no model consistently dominates spatio-temporally, and relative performance is highly context-dependent. This motivates adaptive methods for combining multiple forecasts to obtain improvements and robustness. While combined forecasts have been proposed in the literature, these are achieved either through supervised learning or through prediction with expert advice methods. We introduce AdaWeather, an adaptive framework that combines many probabilistic forecasts using both machine learning as well as mixture of experts to arrive at a unified improved probabilistic forecast. While traditional expert methods develop the regret bounds with respect to the best single expert in hindsight, we extend the algorithm and analysis to show our method has logarithmic regret compared to the best static mixture of experts in hindsight. Empirically, we focus on forecasting temperature, and observe improvements over existing methods.
Abstract:Recent advances in machine learning have produced probabilistic weather forecasting models comparable to state-of-the-art numerical weather predictors. But no model consistently dominates spatio-temporally, and relative performance is highly context-dependent. This motivates adaptive methods for combining multiple forecasts to obtain improvements and robustness. While combined forecasts have been proposed in the literature, these are achieved either through supervised learning or through prediction with expert advice methods. We introduce AdaWeather, an adaptive framework that combines many probabilistic forecasts using both machine learning as well as mixture of experts to arrive at a unified improved probabilistic forecast. While traditional expert methods develop the regret bounds with respect to the best single expert in hindsight, we extend the algorithm and analysis to show our method has logarithmic regret compared to the best static mixture of experts in hindsight. Empirically, we focus on forecasting temperature, and observe improvements over existing methods.
36 pages, 16 figures. Submitted to arXiv. Forecast aggregation for probabilistic weather prediction using offline supervised learning and online prediction with expert advice. Includes theoretical regret guarantees and empirical evaluation on temperature forecasting. Submitted to NeurIPS 2026
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
I.2.6; I.2.8; G.3
arXiv:2606.02663 [cs.LG]
(or arXiv:2606.02663v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.02663 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 207 words
Related coverage
From Shared Demand Patterns to Local Uncertainty: Probabilistic Load Forecasting by Mixing Compact Adaptations
arXiv · Oct 7, 2026
Introducing Timestral
Mistral AI · Oct 15, 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026
Aurora 1.5: Extending open foundation models for weather and Earth-system applications
Microsoft Research · Jul 9, 2026