arXiv：cs.LG· Xiao Wang, Changjian Chen, Zhuo Tang, Rongwen Li, Hongwu Liu, Kenli Li·· 4 小时前AI 评分26
WxFM-XL：将单变量基础模型适配到多站天气预报
WxFM-XL: Adapting Univariate Foundation Models to Multi-Station Weather Forecasting
AI 导读
WxFM-XL 通过引入跨站误差相关先验图与动态融合机制，将单变量时间序列基础模型（如 Sundial、Timer）适配到多站天气预报，动态融合机制可自适应整合空间相关图与误差相关先验图。在多个数据集上，该模型表现优于当前最优基线。相关研究以 arXiv:2610.10057 提交至 cs.LG。
正文
Abstract:With the rise of univariate time series foundation models (e.g., Sundial, Timer), initial efforts have been made to extend them to multivariate settings. However, these models mainly focus on modeling correlations among variables. When they are applied to multi-station weather forecasting, two important factors are often overlooked: (1) the spatial information of stations, and (2) different error priors of different stations relative to the foundation model. In this paper, we propose WxFM-XL, a model for adapting univariate time series foundation models to multi-station weather forecasting. WxFM-XL introduces a cross-station error correlation prior graph to capture stationwise error priors with respect to the foundation model. Building on this, we further propose a dynamic fusion mechanism that adaptively integrates a spatial correlation graph with the error correlation prior graph. Experiments on multiple datasets demonstrate that our model outperforms state of the art baselines.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.10057 [cs.LG] |
| (or arXiv:2610.10057v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10057 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiao Wang [view email]
[v1]
Wed, 7 Oct 2026 13:28:17 UTC (2,346 KB)
来源：arXiv：cs.LG · arxiv.org