aiqbench analysis
This paper introduces $M^2$Weather, a new benchmark designed to systematically evaluate models that jointly handle spatial dependencies across weather stations and physical couplings among variables. By establishing unified protocols and an adapter for missing relationships, the study demonstrates significant performance gains over approaches that treat these factors separately. The work advances machine learning in domain-specific forecasting by providing a rigorous framework for assessing model robustness across national to global scales.
M$^2$Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecasting
arXiv:2610.00370v1 Announce Type: new Abstract: Station weather forecasting is fundamentally shaped by both complex spatial dependencies across stations and strong physical coupling among weather variables. However, existing studies often consider these relationships separately and use different datasets and experimental settings, hindering systematic assessment of their individual and joint contributions. In this paper, we introduce $M^2$Weather, a benchmark for joint multi-station and multi-variable weather forecasting. Through multi-criteria quality control and station stratification, we collect 2,809 high-quality stations with 5 physically coupled weather variables across three spatial scales: France, Europe, and Global. This multi-scale design lets us examine whether conclusions persist from national to global station networks. We also introduce unified training and evaluation protocols to enable fair comparison of different station-variable modeling paradigms. To further examine the benefits of modeling station-variable relationships, we design a lightweight, plug-and-play adapter. With a trained weather forecasting model, this adapter can introduce missing station or variable relationships without retraining the model. This enables fair and efficient investigation of station-variable relationships. Systematic evaluation of 16 representative models shows the benefits of jointly modeling station and variable relationships. Completing missing relationships further reduces MSE for all adapted models on all three datasets. Together, these results identify the complementary information across stations and variables as an important resource for improving station weather forecasting. Our code can be obtained at https://github.com/hnu-vis/M2-Weather.
Abstract:Station weather forecasting is fundamentally shaped by both complex spatial dependencies across stations and strong physical coupling among weather variables. However, existing studies often consider these relationships separately and use different datasets and experimental settings, hindering systematic assessment of their individual and joint contributions. In this paper, we introduce $M^2$Weather, a benchmark for joint multi-station and multi-variable weather forecasting. Through multi-criteria quality control and station stratification, we collect 2,809 high-quality stations with 5 physically coupled weather variables across three spatial scales: France, Europe, and Global. This multi-scale design lets us examine whether conclusions persist from national to global station networks. We also introduce unified training and evaluation protocols to enable fair comparison of different station-variable modeling paradigms. To further examine the benefits of modeling station-variable relationships, we design a lightweight, plug-and-play adapter. With a trained weather forecasting model, this adapter can introduce missing station or variable relationships without retraining the model. This enables fair and efficient investigation of station-variable relationships. Systematic evaluation of 16 representative models shows the benefits of jointly modeling station and variable relationships. Completing missing relationships further reduces MSE for all adapted models on all three datasets. Together, these results identify the complementary information across stations and variables as an important resource for improving station weather forecasting. Our code can be obtained at this https URL.
Machine Learning (cs.LG); Machine Learning (stat.ML)
arXiv:2610.00370 [cs.LG]
(or arXiv:2610.00370v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.00370 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 316 words
Related coverage
News
Quantum Computing Report · Jul 25, 2026
Learning joint probabilistic weather forecasts from station observations alone
arXiv · Oct 8, 2026
A Station-Based Evaluation of Machine Learning-based Weather Forecasting Models in Northern Norway
arXiv · Sep 11, 2026
From Deterministic to Generative Deep Learning for Urban Air Quality Reconstruction from Sparse Observations
arXiv · Jul 29, 2026