Spatiotemporal integration of GCN and E-LSTM networks for PM2.5 forecasting

Abstract

PM2.5, inhalable particles, with a size of 2.5 micrometers or less, negatively impact the environment as well as our health. Monitoring PM2.5 is critical to guard against extreme events by alerting people and initiating actions to alleviate PM2.5′s impacts. Developing PM2.5 forecasting frameworks empowers the authorities to predict extremely polluted events in advance and gives them time to implement necessary strategies in advance (e.g., Action! Days). Understanding the spatiotemporal behavior of PM2.5 and meteorological factors is of significance for having accurate predictions. This study utilizes EPA sensor data to quantify the PM2.5 air quality index (AQI) and meteorological factors such as temperature over 2015–2019 across Michigan, USA. Here, a spatiotemporal deep neural structure is proposed through integrating graph convolutional neural (GCN) and exogenous long short-term memory (E-LSTM) networks to incorporate spatial and temporal patterns within PM2.5 AQI and meteorological factors for predicting PM2.5 AQI. Results illustrate that not only does our proposed framework outperform the traditional approaches such as LSTM and E-LSTM, but also it is robust against the network structure of EPA stations. The study's findings demonstrate that the integration of GCN with E-LSTM significantly enhances the accuracy of PM2.5 AQI predictions compared to traditional models. This advancement indicates a promising direction for environmental monitoring, offering improved forecasting tools that can aid in timely and effective decision-making for air quality management and public health protection.

Keywords

• PM2.5 AQI forecasting
• Graph convolutional neural network
• Exogenous long short-term memory
• Air quality prediction
• Urban air pollution