A flexible grey Fourier model based on integral matching for forecasting seasonal PM2.5 time series. (September 2022)

• Record Type: Journal Article
• Authors: Wang, Xiaolei; Xie, Naiming; Yang, Lu
• Is Part Of: Chaos, solitons and fractals. Volume 162(2022)
• Publication Date: 2022-09
• Subjects: Grey Fourier model -- Seasonal time series -- Integral matching -- Order selection -- Air pollution prediction; Chaotic behavior in systems -- Periodicals; Solitons -- Periodicals; Fractals -- Periodicals; Chaotic behavior in systems; Fractals; Solitons; Periodicals; 003.7
• DOI: 10.1016/j.chaos.2022.112417
• Languages: English
• ISSNs: 0960-0779

Abstract

Abstract: The PM2.5 in each city exhibits seasonal and trend variations, but its seasonal pattern differed regionally. Under the novel grey modelling framework, a flexible grey Fourier model is developed by introducing the Fourier series to approximate the seasonal forcing. An integral matching method is employed to estimate the structural parameters and initial value simultaneously, then a data-driven order selection approach is utilized to accommodate various seasonal features. Next, Monte-Carlo simulation is designed to verify the effectiveness of the order selection approach and the influence of noise level. Finally, this model is established for predicting the monthly PM2.5 of four capital cities in the Yangtze River Delta of China. The results indicate that it not only reflects the different seasonal patterns of the four cities but also performs well compared to the seven competitive models.