Forecasting hourly PM2.5 concentrations based on decomposition-ensemble-reconstruction framework incorporating deep learning algorithms

Abstract

Accurate predictions of hourly PM_2.5 concentrations are crucial for preventing the harmful effects of air pollution. In this study, a new decomposition-ensemble framework incorporating the variational mode decomposition method (VMD), econometric forecasting method (autoregressive integrated moving average model, ARIMA), and deep learning techniques (convolutional neural networks (CNN) and temporal convolutional network (TCN)) was developed to model the data characteristics of hourly PM_2.5 concentrations. Taking the PM_2.5 concentration of Lanzhou, Gansu Province, China as the sample, the empirical results demonstrated that the developed decomposition-ensemble framework is significantly superior to the benchmarks with the econometric model, machine learning models, basic deep learning models, and traditional decomposition-ensemble models, within one-, two-, or three-step-ahead. This study verified the effectiveness of the new prediction framework to capture the data patterns of PM_2.5 concentration and can be employed as a meaningful PM_2.5 concentrations prediction tool.