Weather Forecasting is an attractive challengeable task due to its influence on human life and complexity in atmospheric motion. Supported by massive historical observed time series data, the task is suitable for data-driven approaches, especially deep neural networks. Recently, the Graph Neural Networks (GNNs) based methods have achieved excellent performance for spatio-temporal forecasting. However, the canonical GNNs-based methods only individually model the local graph of meteorological variables per station or the global graph of whole stations, lacking information interaction between meteorological variables in different stations. In this paper, we propose a novel Hierarchical Spatio-Temporal Graph Neural Network (HiSTGNN) to model cross-regional spatio-temporal correlations among meteorological variables in multiple stations. An adaptive graph learning layer and spatial graph convolution are employed to construct self-learning graph and study hidden dependency among nodes of variable-level and station-level graph. For capturing temporal pattern, the dilated inception as the backbone of gate temporal convolution is designed to model long and various meteorological trends. Moreover, a dynamic interaction learning is proposed to build bidirectional information passing in hierarchical graph. Experimental results on three real-world meteorological datasets demonstrate the superior performance of HiSTGNN beyond 7 baselines and it reduces the errors by 4.2% to 11.6% especially compared to state-of-the-art weather forecasting method.
翻译:天气预报是一项具有吸引力的挑战性任务, 因为它对人类生活的影响和大气运动的复杂性。 在大量历史观测的时间序列数据的支持下, 任务适合于数据驱动的方法, 特别是深神经网络。 最近, 基于图形神经网络(GNNS) 的方法在时空预报方面取得了优异的性能。 然而, 基于光学 GNNS 的方法仅个别地建模每个站点的当地气象变量图或整个站点的全球图, 缺乏不同站点气象变量之间的信息互动。 在本文中, 我们提议建立一个新型的高层空间- 时空图神经网络( HISTGNNN), 以模拟多个站点气象变量之间的跨区域空间- 时空关系。 采用适应性图学习层和空间图变异点图的组合来构建自学图表, 研究各站级和站级图的节点之间的隐性依赖性。 为了捕捉时间模式, 门时间演变的骨干结是为了模拟各种气象趋势。 此外, 一种动态互动学习计划(HSTGNNIN6) 将真实的双向模型用于测试, 水平图中, 。