Hubei Key Laboratory of Quantitative Remote Sensing of Land and Atmosphere, School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China.
Hubei Key Laboratory of Quantitative Remote Sensing of Land and Atmosphere, School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China; Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, China.
Environ Int. 2023 Jun;176:107971. doi: 10.1016/j.envint.2023.107971. Epub 2023 May 12.
The observation-based air pollution forecasting method has high computational efficiency over traditional numerical models, but a poor ability in long-term (after 6 h) forecasting due to a lack of detailed representation of atmospheric processes associated with the pollution transport. To address such limitation, here we propose a novel real-time air pollution forecasting model that applies a hybrid graph deep neural network (GNN_LSTM) to dynamically capture the spatiotemporal correlations among neighborhood monitoring sites to better represent the physical mechanism of pollutant transport across the space with the graph structure which is established with features (angle, wind speed, and wind direction) of neighborhood sites to quantify their interactions. Such design substantially improves the model performance in 72-hour PM forecasting over the whole Beijing-Tianjin-Hebei region (overall R increases from 0.6 to 0.79), particularly for polluted episodes (PM concentration > 55 µg/m) with pronounced regional transport to be captured by GNN_LSTM model. The inclusion of the AOD feature further enhances the model performance in predicting PM over the sites where the AOD can inform additional aloft PM pollution features related to regional transport. The importance of neighborhood site (particularly for those in the upwind flow pathway of the target area) features for long-term PM forecast is demonstrated by the increased performance in predicting PM in the target city (Beijing) with the inclusion of additional 128 neighborhood sites. Moreover, the newly developed GNN_LSTM model also implies the "source"-receptor relationship, as impacts from distanced sites associated with regional transport grow along with the forecasting time (from 0% to 38% in 72 h) following the wind flow. Such results suggest the great potential of GNN_LSTM in long-term air quality forecasting and air pollution prevention.
基于观测的空气污染预测方法比传统的数值模型具有更高的计算效率，但由于缺乏与污染传输相关的大气过程的详细表示，其长期（6 小时后）预测能力较差。为了解决这一限制，我们提出了一种新的实时空气污染预测模型，该模型应用混合图深度学习神经网络（GNN_LSTM）来动态捕捉邻域监测站点之间的时空相关性，以更好地表示污染物在空间中的传输物理机制，图结构是通过邻域站点的特征（角度、风速和风向）建立的，以量化它们之间的相互作用。这种设计显著提高了整个京津冀地区 72 小时 PM 预测的模型性能（整体 R 值从 0.6 增加到 0.79），特别是对于 GNN_LSTM 模型能够捕捉到的污染事件（PM 浓度>55µg/m），这些事件具有明显的区域传输特征。包含 AOD 特征进一步提高了模型在预测站点 PM 方面的性能，这些站点的 AOD 可以提供与区域传输相关的高空 PM 污染特征。通过包含额外的 128 个邻域站点，邻域站点（特别是目标区域上风路径的站点）特征对长期 PM 预测的重要性得以证明，从而提高了目标城市（北京）的 PM 预测性能。此外，新开发的 GNN_LSTM 模型还暗示了“源”-“受体”关系，因为与区域传输相关的远距离站点的影响随着风向而增长（在 72 小时内从 0%增长到 38%）。这些结果表明，GNN_LSTM 在长期空气质量预测和空气污染预防方面具有巨大的潜力。
