标题： S$^2$变压器：用于全球气象预报的可扩展结构变压器 显示英文标题

标题： S$^2$Transformer: Scalable Structured Transformers for Global Station Weather Forecasting

摘要： 全球站点天气预报（GSWF）是一个关键的气象研究领域，对能源、航空和农业至关重要。 现有的时间序列预测方法在进行大规模全球站点预测时，往往忽略或单向建模空间相关性。 这与全球天气系统的观测内在本质相矛盾，限制了预测性能。 为了解决这个问题，本文提出了一种新颖的空间结构注意力模块。 它将空间图划分为一组子图，并实例化子图内注意力以学习每个子图内的局部空间相关性，同时通过子图间注意力将节点聚合为子图表示，以实现子图之间的信息传递——同时考虑空间邻近性和全局相关性。 基于该模块，我们开发了一个多尺度时空预测模型 S$^2$Transformer，通过逐步扩展子图规模来构建。 该模型既具有可扩展性，又能生成结构化的空间相关性，同时易于实现。 实验结果表明，它可以在低运行成本下比时间序列预测基线方法提升高达16.8%的性能。 显示英文摘要

摘要： Global Station Weather Forecasting (GSWF) is a key meteorological research area, critical to energy, aviation, and agriculture. Existing time series forecasting methods often ignore or unidirectionally model spatial correlation when conducting large-scale global station forecasting. This contradicts the intrinsic nature underlying observations of the global weather system, limiting forecast performance. To address this, we propose a novel Spatial Structured Attention Block in this paper. It partitions the spatial graph into a set of subgraphs and instantiates Intra-subgraph Attention to learn local spatial correlation within each subgraph, and aggregates nodes into subgraph representations for message passing among the subgraphs via Inter-subgraph Attention -- considering both spatial proximity and global correlation. Building on this block, we develop a multiscale spatiotemporal forecasting model S$^2$Transformer by progressively expanding subgraph scales. The resulting model is both scalable and able to produce structured spatial correlation, and meanwhile, it is easy to implement. The experimental results show that it can achieve performance improvements up to 16.8% over time series forecasting baselines at low running costs.