Daily urban air quality index forecasting based on variational mode decomposition, sample entropy and LSTM neural network. (October 2019)

• Record Type: Journal Article
• Authors: Wu, Qunli; Lin, Huaxing
• Is Part Of: Sustainable cities and society. Volume 50(2019)
• Publication Date: 2019-10
• Subjects: Air quality index (AQI) forecasting -- Variational mode decomposition (VMD) -- Sample entropy (SE) -- Long short-term memory (LSTM) -- Neural network; Sustainable urban development -- Periodicals; Sustainable buildings -- Periodicals; Urban ecology (Sociology) -- Periodicals; 307.76
• DOI: 10.1016/j.scs.2019.101657
• Languages: English
• ISSNs: 2210-6707

Abstract

Highlights: A new hybrid model is developed for AQI forecasting. VMD-SE is applied to decompose and recombine AQI series. LSTM neural network is employed to forecast SE-BIMF. The proposed hybrid model outperforms other hybrid models. Abstract: An accurate and effective air quality index (AQI) forecasting is one of the necessary conditions for the promotion of urban public health, and to help society to be sustainable notwithstanding the effects of air pollution. This study proposes a hybrid AQI forecasting model to enhance forecasting accuracy. Variational mode decomposition (VMD) was applied to decompose the original AQI series into different sub-series with various frequencies. Then, sample entropy (SE) was applied to recombine the sub-series to solve the issues of over-decomposition and computational burden. Next, a long short-term memory (LSTM) neural network was established, to forecast those new sub-series, following which the ultimate AQI forecast could be obtained, by accumulating prediction values from each sub-series. The results illustrated that: (1) the proposed VMD-SE-LSTM model displayed superior capacity for daily urban AQI forecasting, as shown using test case data from Beijing and Baoding; (2) when the proposed model was compared with other models, the results indicated that VMD-SE-LSTM model comprehensively captured the characteristics of the original AQI series. Besides, the proposed model had a high rate of correct AQI class forecasting, which existing single models cannot achieve, while other hybrid models can only reflect AQI series trends with limited prediction accuracy.