发表机构
Hunan University; China Meteorological Administration; Hunan Provincial Meteorological Bureau（湖南大学; 中国气象局; 湖南省气象局）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
STCFormer提出一种自适应时空Transformer，通过动态聚类和簇引导注意力平衡局部与全局信息，在八个天气预测任务上取得最优性能。
AI 中文摘要
基于站点的天气预报支撑着日常生活和经济活动，然而准确的预测需要对站点间复杂的空间依赖关系进行建模。近期基于聚类的选择性建模为密集的站点间交互提供了一种有前景的替代方案。然而，在观测窗口内共享的分组可能掩盖站点关系的局部变化，而仅依靠簇内交互可能会遗漏重要的全局上下文。选择性交互相对于密集连接的理论优势也尚未得到充分理解。为此，我们提出了STCFormer，一种自适应时空Transformer，它根据每个时间片内站点的局部演化动态地对站点进行分组。其簇引导注意力模块结合了簇内的细粒度局部注意力和基于区域状态汇总的全局注意力，使得每个站点都能访问其自身簇之外的信息。我们进一步证明，簇条件局部注意力的导出Lipschitz上界不大于其全连接对应物，这解释了潜在的鲁棒性优势，并启发了InfoLoss的设计。在涵盖八个温度和风力预测任务的三个真实世界天气数据集上的实验表明，STCFormer在所有八个任务上均取得了最低的24小时均方误差，并在跨指标和预测时域的48项比较中排名第一或第二。消融研究和案例研究进一步证实了局部自适应分组和互补的局部-全局交互的益处。我们的代码可在以下https URL获取。
英文摘要
Station-based weather forecasting supports daily life and economic activity, yet accurate forecasts require modeling complex spatial dependencies among stations. Recent clustering-based selective modeling offers a promising alternative to dense inter-station interactions. However, a grouping shared across an observation window may obscure local changes in station relationships, while intra-cluster interactions alone may miss important global context. The theoretical advantages of selective interactions over dense connectivity also remain insufficiently understood. We therefore propose STCFormer, an adaptive spatio-temporal Transformer that dynamically groups stations according to their local evolution within each temporal patch. Its Cluster-Guided Attention Block combines fine-grained local attention within clusters and global attention over regional state summaries, allowing each station to access information beyond its own cluster. We further show that a derived Lipschitz upper bound for cluster-conditioned local attention is no larger than its fully connected counterpart, explaining a potential robustness benefit and motivating the design of InfoLoss. Experiments on three real-world weather datasets spanning eight temperature and wind forecasting tasks show that STCFormer achieves the lowest 24-hour mean squared error on all eight tasks and ranks first or second in 47 of 48 comparisons across metrics and forecasting horizons. Ablations and case studies further confirm the benefits of locally adaptive grouping and complementary local-global interactions. Our code can be obtained at https://github.com/hnu-vis/STCFormer.
Comments34 pages, 12 figures
