A Novel Hybrid Machine Learning Method (OR-ELM-AR) Used in Forecast of PM2.5 Concentrations and Its Forecast Performance Evaluation

Abstract

Accurate forecast of PM2.5 pollution is highly needed for the timely prevention of haze pollution in many cities suffered from frequent haze pollution. In this work, an online recurrent extreme learning machine (OR-ELM) technique with online data update was used in the forecast of PM2.5 pollution for the first time, and a hybrid model (OR-ELM-AR) by combining autoregressive (AR) model was proposed to enhance its forecast ability to capture the variations of hourly PM2.5 concentration. Evaluation of forecast performances in terms of pollution levels, forecast times, spatial distributions were conducted over the Yangtze River Delta (YRD) region, China. Results indicated that the OR-ELM-AR model could quickly respond to short-term changes and had better forecast performance. Therefore, the OR-ELM-AR model is a promising tool for air pollution forecast of supporting the government to take urgent actions to reduce the frequency and severity of haze pollution in cities or regions.