Institute of Information Science, Academia Sinica, Taipei, Taiwan.
Social Networks and Human Centered Computing Program, Taiwan International Graduate Program, Taipei, Taiwan.
PLoS One. 2023 Mar 10;18(3):e0282471. doi: 10.1371/journal.pone.0282471. eCollection 2023.
Accurate PM2.5 prediction is part of the fight against air pollution that helps governments to manage environmental policy. Satellite Remote sensing aerosol optical depth (AOD) processed by The Multi-Angle Implementation of Atmospheric Correlation (MAIAC) algorithm allows us to observe the transportation of remote pollutants between regions. The paper proposes a composite neural network model, the Remote Transported Pollutants (RTP) model, for such long-range pollutant transportation that predicts more accurate local PM2.5 concentrations given such satellite data. The proposed RTP model integrates several deep learning components and learns from the heterogeneous features of various domains. We also detected remote transportation pollution events (RTPEs) at two reference sites from the AOD data. Extensive experiments using real-world data show that the proposed RTP model outperforms the base model that does not account for RTPEs by 17%-30%, 23%-26% and 18%-22% and state-of-the-art models that account for RTPEs by 12%-22%, 12%-14%, and 10%-11% at +4h to +24h, +28h to +48 hours, and +52h to +72h hours respectively.
准确的 PM2.5 预测是对抗空气污染的一部分，有助于政府管理环境政策。卫星遥感气溶胶光学厚度（AOD）由多角度大气相关实施（MAIAC）算法处理，可以观察到远程污染物在区域之间的运输。本文提出了一种复合神经网络模型，即远程传输污染物（RTP）模型，用于这种远程污染物运输，该模型可以根据卫星数据预测更准确的局部 PM2.5 浓度。所提出的 RTP 模型集成了几个深度学习组件，并从各个领域的异构特征中进行学习。我们还从 AOD 数据中的两个参考站点检测到远程传输污染事件（RTPE）。使用真实数据的广泛实验表明，与不考虑 RTPE 的基础模型相比，所提出的 RTP 模型在+4h 到+24h、+28h 到+48h 和+52h 到+72h 时分别提高了 17%-30%、23%-26%和 18%-22%，与考虑 RTPE 的最新模型相比提高了 12%-22%、12%-14%和 10%-11%。
