PM_2.5 Forecast Based on a Multiple Attention Long Short-Term Memory (MAT-LSTM) Neural Networks

Abstract

Air pollution, especially by particulate matter with diameters less than 2.5 μm (PM_2.5), is a serious threat to public health. The accurate prediction of PM_2.5 concentration is significant for air pollution control and the prevention of health issues. However, accurate prediction and forecasting of PM_2.5 has been challenging. In this study, a multiple attention (MAT) mechanism based on multilayer perception, which includes monitoring site attention, time feature attention, and weather attention, was designed to obtain the spatial-temporal and meteorological dependences of PM_2.5. A hybrid deep learning method based on MAT long short-term memory (MAT-LSTM) neural networks is proposed to predict PM_2.5 concentration. To validate the effectiveness of the proposed model, hourly air pollution, and meteorological measurements were collected at 10 monitoring sites in Hefei City from May 13, 2014 to March 21, 2020. Comparison experiments were performed using the MAT-LSTM model, recurrent neural network (RNN), back propagation (BP), and LSTM neural network models. The comparison of the results demonstrated that the MAT-LSTM model was superior to the baseline models and achieved reductions of 86.44%, 69.64%, and 35.2% in the mean absolute percentage error (MAPE) compared with RNN, BP, and LSTM, respectively. In addition, the PM_2.5 forecast experiments were conducted at different time steps from 1 to 12 h. The results show that the proposed model performs well and exhibits an MAPE of 17.86% at the future time step of 1 h, and the prediction performance of the proposed model is satisfactory, even for the next 12-h forecast.

Keywords:

• Air pollution
• multiple attention long short-term memory (MAT-LSTM) neural network
• particulate matter
• PM_2.5 forecasting

Additional information

Funding

This work was supported by the Nature Science Key Fund of Anhui Education Department (Grant Number KJ2019A0877) and Science Research Team of Anhui Xinhua University (Grant Number Kytd201902).