A Graph Attention Recurrent Neural Network Model for PM_2.5 Prediction: A Case Study in China from 2015 to 2022

Abstract

Accurately predicting PM2.5 is a crucial task for protecting public health and making policy decisions. In the meanwhile, it is also a challenging task, given the complex spatio-temporal patterns of PM2.5 concentrations. Recently, the utilization of graph neural network (GNN) models has emerged as a promising approach, demonstrating significant advantages in capturing the spatial and temporal dependencies associated with PM2.5 concentrations. In this work, we collected a comprehensive dataset spanning 308 cities in China, encompassing data on seven pollutants as well as meteorological variables from January 2015 to September 2022. To effectively predict the PM2.5 concentrations, we propose a graph attention recurrent neural network (GARNN) model by taking into account both meteorological and geographical information. Extensive experiments validated the efficiency of the proposed GARNN model, revealing its superior performance compared to other existing methods in terms of predictive capabilities. This study contributes to advancing the understanding and prediction of PM2.5 concentrations, providing a valuable tool for addressing environmental challenges.

Keywords

• PM_2.5 concentration prediction
• graph neural network
• recurrent neural network
• attention mechanism