Affiliations: [a]
College of Earth and Environmental Sciences, Lanzhou University, Lanzhou, China
| [b]
Key Laboratory for Environmental Pollution Prediction and Control, Gansu Province, Lanzhou, China
Correspondence:
[*]
Corresponding author. Yan Tao, College of Earth and Environmental Sciences, Lanzhou University, Lanzhou 73000, China. E-mail: [email protected].
Abstract: Air is regarded as one of a fundamental element for the survival of human and other living creatures. Daily PM10 concentration forecasting is a useful measure that is applied to the prevention and control of work in advance. This paper proposes a multiscale fusion support vector regression (MFSVR) method for forecasting daily PM10 concentration. The method uses stationary wavelet transform (SWT) to decompose original time series of daily PM10 concentration into different scales, of which the information represents wavelet coefficients of PM10 concentration. At each scale, wavelet coefficients are used for training a support vector regression (SVR) model. The estimated coefficients of the SVR outputs for all of the scales applied to the reconstruction of the prediction result by the inverse SWT. To enhance forecasting of the MFSVR, a feature fusion approach that bases on partial least squares is adopted to extract the original features and reduce dimensions for input variables of the SVR model. The experimental confirmation of the proposed method is tested by applying the data of four monitoring stations between 1/1/2015 and 26/12/2015 in Lanzhou, China. The results indicate that the MFSVR approach can precisely forecast daily PM10 concentration on the basis of mean absolute error, mean absolute percentage error, root mean square error and correlation coefficient criteria. This method shows a potential prospect that can be implemented in air quality prediction systems in other areas.
Keywords: PM10 forecasting, multiscale, stationary wavelet transform, partial least squares, support vector regression
