Optimal-combined model for air quality index forecasting: 5 cities in North China

Abstract

Air pollution forecasting is significant for public health and controlling pollution, and statistical methods are important air pollution forecasting techniques. Nevertheless, the research of AQI (air quality index) forecasting is very rare. So an accurate and stable AQI forecasting model is very urgent and necessary. For the high complex, volatile and nonlinear AQI series, this research presents a novel optimal-combined model based on CEEMD (complementary ensemble empirical mode decomposition), PSOGSA (particle swarm optimization and gravitational search algorithm), PSO (particle swarm optimization) and combined forecasting method. The proposed model effectively solves the blind combined forecasting. AQI series forecasts of five cities in North China show that the proposed model has the highest correct rate of forecasting classifications compared with the candidates. Totally, the presented model has the following advantages compared with the candidates: more robust forecasting performance, smaller forecasting error and better generalization ability.