A decomposition and ensemble model based on GWO and Differential Evolution algorithm for PM_2.5 concentration forecasting

Article type: Research Article

Authors: Zhou, Jiaqi | Wu, Tingming | Yu, Xiaobing^{; *} | Wang, Xuming

Affiliations: Research Institute for Risk Governance and Emergency Decision-Making, School of Management Science and Engineering, Nanjing University of Information Science & Technology, Nanjing, China

Correspondence: [*] Corresponding author. Xiaobing Yu, Research Institute for Risk Governance and Emergency Decision-Making, School of Management Science and Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China. Email: yuxb111@163.com.

Abstract: Accurate and reliable prediction of PM2.5 concentrations is the basis for appropriate warning measures, and a single prediction model is often ineffective. In this paper, we propose a novel decomposition-and-ensemble model to predict the concentration of PM2.5. The model utilizes Ensemble Empirical Mode Decomposition (EEMD) to decompose PM2.5 series, Support Vector Regression (SVR) to predict each Intrinsic Mode Function (IMF), and a hybrid algorithm based on Differential Evolution (DE) and Grey Wolf Optimizer (GWO) to optimize SVR parameters. The proposed prediction model EEMD-SVR-DEGWO is employed to forecast the concentration of PM2.5 in Guangzhou, Wuhan, and Chongqing of China. Compared with six prediction models, the proposed EEMD-SVR-DEGWO is a reliable predictor and has achieved competitive results.

Keywords: PM_2.5, prediction, decomposition-and-ensemble, support vector regression

DOI: 10.3233/JIFS-230343

Journal: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 2, pp. 2497-2512, 2023