M2Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecasting
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 M2Weather, 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.
Related
- STCFormer: Adaptive Spatio-Temporal Modeling with Dynamic Cluster Transformer for Station-based Weather Forecasting
- Learning joint probabilistic weather forecasts from station observations alone
- Forecasting and Low-Carbon Demand Response Scheduling of Crane-Group Station-Service Loads for Grid-Friendly Hydropower Station Operation
- Station-specific thunderstorm forecasting using climate predictors with seasonal decomposition analysis in Bangladesh’s most vulnerable regions
- SDECast: Probabilistic Weather Forecasting in Continuous Time with Neural SDEs
BibTeX
@misc{li2026m2weather,
title = {{M$^2$Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecasting}},
author = {Rongwen Li and Xiao Wang and Mingyang Wang and Hongwu Liu and Changjian Chen and Zhuo Tang and Kenli Li},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.00370},
eprint = {2610.00370},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.00370},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - M^2Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecasting
AU - Rongwen Li
AU - Xiao Wang
AU - Mingyang Wang
AU - Hongwu Liu
AU - Changjian Chen
AU - Zhuo Tang
AU - Kenli Li
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.00370
UR - https://arxiv.org/abs/2610.00370
AB - 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^2Weather, 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.
ER -