High-resolution spatiotemporal prediction of PM concentration based on mobile monitoring and deep learning.

Journal: Environmental pollution (Barking, Essex : 1987)
PMID:

Abstract

Obtaining the high-resolution distribution characteristics of urban air pollutants is crucial for effective pollution control and public health. In order to fulfill it, mobile monitoring offers a novel and practical approach compared to traditional fixed monitoring methods. However, the sparsity of mobile monitoring data still makes it a challenge to recover the high-resolution pollutant concentration across an entire area. To tackle the sparsity issue and fulfill a prediction of the spatiotemporal distribution of PM, a high-resolution urban PM prediction method was proposed based on mobile monitoring data in this study. This method enables prediction with a spatial resolution of 500m × 500m and a temporal resolution of 1 h. First, a Light Gradient Boosting Machine (LightGBM) was trained using mobile monitoring of PM concentration and exogenous features to obtain complete spatiotemporal PM concentration. Second, a model consisting of Convolutional Neural Network and Transformer (CNN-Transformer) with a customised loss function was established to predict high-resolution PM concentration based on complete spatiotemporal data. The method was validated using real-world data collected from Cangzhou, China. The numerical results from cross-validation showed an R of 0.925 for imputation and 0.887 for prediction, demonstrating this method is suitable for high-resolution spatiotemporal prediction of PM concentration based on mobile monitoring data.

Authors

  • Yi-Zhou Wang
    School of Electronic Engineering and Computer Science, Peking University, No. 5 Yiheyuan Rd., Haidian District, Beijing, 100871, China.
  • Hong-di He
    Center for ITS and UAV Applications Research, State Key Laboratory of Ocean Engineering, School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China. Electronic address: hongdihe@sjtu.edu.cn.
  • Hai-Chao Huang
    Center for Intelligent Transportation Systems and Unmanned Aerial Systems Applications, State-Key Laboratory of Ocean Engineering, School of Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China.
  • Jin-Ming Yang
    MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, 200240, China.
  • Zhong-Ren Peng
    International Center for Adaptation Planning and Design, College of Design, Construction and Planning, University of Florida, PO Box 115706, Gainesville, FL, 32611-5706, USA.