Abstract:

In the spatiotemporal hybrid models that integrate meteorological， spatial， and temporal information， the modeling of temporal changes is usually done in one-dimensional space. To solve the problems that one-dimensional sequences are limited in sliding windows and is lack of the flexibility of multi-scale feature extraction， a Multi-domain SpatioTemporal Hierarchical Graph Neural Network （MST-HGNN） model was proposed. Firstly， two levels of hierarchical graphs were constructed， namely， city-wide global scale one and station-level local scale one， so as to perform spatial relationship learning. Secondly， the one-dimensional air quality sequences were transformed into a set of two-dimensional tensors based on multiple periods， and multi-scale convolution in two-dimensional space was used to capture frequency domain features by periodic decoupling. At the same time， Long Short-Term Memory （LSTM） network in one-dimensional space was employed to fit temporal features. Finally， to avoid redundant information aggregation， a gating mechanism fusion module was designed for multi-domain feature fusion of frequency domain and temporal domain features. Experimental results on Urban-Air dataset and the Yangtze River Delta city cluster dataset show that compared with Multi-View Multi-Task Spatiotemporal Graph Convolutional Network model （M2）， the proposed model has lower Mean Absolute Error （MAE） and Root Mean Squared Error （RMSE） than the comparison model in predicting air quality at the 1 h， 3 h， 6 h， and 12 h. It can be seen that MST-HGNN can decouple complex time patterns in the frequency domain， compensate for the limitations of temporal feature modeling using frequency domain information， and predict air quality changes more comprehensively by combining time domain information.

Key words: air quality prediction, multi-domain feature fusion, spatiotemporal feature, periodic decoupling, gating mechanism fusion, Graph Neural Network (GNN)

摘要：

在协同融合气象、空间和时间三大信息的时空混合模型中，时间变化建模通常在一维空间中完成。针对一维序列局限于滑动窗口和缺乏对多尺度特征的灵活提取的问题，提出一种多域时空层次图神经网络（MST-HGNN）模型。首先，构建城市全局尺度和站点局部尺度的两级层次图，从而进行空间关系学习；其次，将一维空气质量序列转换为一组基于多个周期的二维张量，并在二维空间上通过多尺度卷积进行周期解耦以捕获频域特征；同时，在一维空间中利用长短期记忆（LSTM）网络拟合时域特征；最后，为避免聚合冗余信息，设计一种门控机制融合模块用于频域和时域特征的多域特征融合。在Urban-Air数据集和长三角城市群数据集上的实验结果表明，相较于多视图多任务时空图卷积网络模型（M2），所提模型在预测第1 h、3 h、6 h、12 h空气质量的平均绝对误差（MAE）和均方根误差（RMSE）均低于对比模型。可见，MST-HGNN能在频域上解耦复杂时间模式，利用频域信息弥补时域特征建模的局限性，并结合时域信息更全面地预测空气质量变化。

关键词: 空气质量预测, 多域特征融合, 时空特征, 周期解耦, 门控机制融合, 图神经网络