A new hybrid prediction model of air quality index based on secondary decomposition and improved kernel extreme learning machine. (October 2022)

• Record Type: Journal Article
• Authors: Li, Guohui; Tang, Yuze; Yang, Hong
• Is Part Of: Chemosphere. Volume 305(2022)
• Publication Date: 2022-10
• Subjects: Air quality index prediction -- Multivariate multiscale dispersion entropy -- Complete ensemble empirical mode decomposition with adaptive noise -- Variational mode decomposition -- Kernel extreme learning machine; Pollution -- Periodicals; Pollution -- Physiological effect -- Periodicals; Environmental sciences -- Periodicals; Atmospheric chemistry -- Periodicals; 551.511
• DOI: 10.1016/j.chemosphere.2022.135348
• Languages: English
• ISSNs: 0045-6535

Abstract

Abstract: Air quality index (AQI) prediction is important to control air pollution. To improve its accuracy, a new hybrid prediction model of AQI based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), multivariate multiscale dispersion entropy (mvMDE), variational mode decomposition optimized by bald eagle search (BES) algorithm (BVMD) and kernel extreme learning machine optimized by rat swarm optimizer (RSO) algorithm (RSO-KELM), named CEEMDAN-mvMDE-BVMD-RSO-KELM, is proposed. Firstly, AQI series is decomposed by CEEMDAN to obtain multiple intrinsic mode function (IMF) components, and each IMF component's complexity is calculated by mvMDE. Secondly, VMD optimized by BES algorithm, named BVMD, is proposed to solve the problem of choosing the decomposition level K and penalty factor α of VMD, and BVMD is used to perform the secondary decomposition of high complexity components. Thirdly, the penalty coefficient and kernel parameter of KELM optimized by RSO algorithm, named RSO-KELM, is proposed, and all IMF components are predicted by RSO-KELM. Finally, the final prediction results are obtained by reconstructing the prediction results of all IMF components. The objective of this study is to propose a new hybrid prediction model of AQI based on secondary decomposition and improved KELM. Taking Shanghai, Beijing and Xi'an as examples, the results show that compared with the comparison models, the proposed model has the highest prediction accuracy. Graphical abstract: Image 1 Highlights: Propose a new hybrid prediction model of air quality index. Propose optimize VMD parameters by BES algorithm. Propose optimize KELM parameters by RSO algorithm. Apply mvMDE to judge the complexity of each decomposition component.