Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, China; Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo 315200, China.
Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo 315200, China; School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
Environ Int. 2024 Oct;192:108997. doi: 10.1016/j.envint.2024.108997. Epub 2024 Sep 11.
Accurate air quality forecasting is crucial for public health, environmental monitoring and protection, and urban planning. However, existing methods fail to effectively utilize multi-scale information, both spatially and temporally. There is a lack of integration between individual monitoring stations and city-wide scales. Temporally, the periodic nature of air quality variations is often overlooked or inadequately considered. To overcome these limitations, we conduct a thorough analysis of the data and tasks, integrating spatio-temporal multi-scale domain knowledge. We present a novel Multi-spatial Multi-temporal air quality forecasting method based on Graph Convolutional Networks and Gated Recurrent Units (M2G2), bridging the gap in air quality forecasting across spatial and temporal scales. The proposed framework consists of two modules: Multi-scale Spatial GCN (MS-GCN) for spatial information fusion and Multi-scale Temporal GRU (MT-GRU) for temporal information integration. In the spatial dimension, the MS-GCN module employs a bidirectional learnable structure and a residual structure, enabling comprehensive information exchange between individual monitoring stations and the city-scale graph. Regarding the temporal dimension, the MT-GRU module adaptively combines information from different temporal scales through parallel hidden states. Leveraging meteorological indicators and four air quality indicators, we present comprehensive comparative analyses and ablation experiments, showcasing the higher accuracy of M2G2 in comparison to nine currently available advanced approaches across all aspects. The improvements of M2G2 over the second-best method on RMSE of 72-h future predictions are as follows: PM: 6%∼10%; PM: 5%∼7%; NO: 5%∼16%; O: 6%∼9%. Furthermore, we demonstrate the effectiveness of each module of M2G2 by ablation study. We conduct a sensitivity analysis of air quality and meteorological data, finding that the introduction of O adversely impacts the prediction accuracy of PM.
准确的空气质量预测对于公共健康、环境监测和保护以及城市规划至关重要。然而，现有的方法未能有效地利用多尺度的时空信息，并且在个体监测站和全市范围内缺乏整合。在时间上，空气质量变化的周期性往往被忽视或考虑不足。为了克服这些限制，我们对数据和任务进行了全面分析，整合了时空多尺度领域知识。我们提出了一种新的基于图卷积网络和门控循环单元的多空间多时间空气质量预测方法（M2G2），弥合了时空尺度上空气质量预测的差距。该框架由两个模块组成：用于空间信息融合的多尺度空间 GCN（MS-GCN）和用于时间信息集成的多尺度时间 GRU（MT-GRU）。在空间维度上，MS-GCN 模块采用了双向可学习结构和残差结构，实现了个体监测站和城市规模图之间的全面信息交换。在时间维度上，MT-GRU 模块通过并行隐藏状态自适应地组合来自不同时间尺度的信息。利用气象指标和四个空气质量指标，我们进行了全面的对比分析和消融实验，展示了 M2G2 在各个方面都比目前可用的九种先进方法具有更高的准确性。M2G2 相对于第二好方法在 72 小时未来预测 RMSE 上的改进如下：PM：6%∼10%；PM：5%∼7%；NO：5%∼16%；O：6%∼9%。此外，我们通过消融研究展示了 M2G2 的每个模块的有效性。我们对空气质量和气象数据进行了敏感性分析，发现 O 的引入对 PM 的预测精度产生了不利影响。
