AI Summary & Key Takeaways
AI InsightThe results show that the W-BPNN model has better forecasting performance for thethree air pollutants than mono-BPNN model in terms of the statistics indexes (mean absolute percentageerror, root mean square error and correlation coefficient criteria) and the forecasting accuracy of thenumber of relevant days of individual air quality index.
📌 3 Key Takeaways
Özet
Air quality forecasting is an effective way to protect public health by providing an early warning againstharmful air pollutants. In this paper, a model W-BPNN using wavelet technique and back propagationneural network (BPNN) is developed and tested to forecast daily air pollutants (PM10, SO2, and NO2)concentrations. Firstly, stationary wavelet transform (SWT) is applied to decompose historical time seriesof daily air pollutants concentrations into different scales, of which the information represents waveletcoefficients of air pollutant concentration. Secondly, the wavelet coefficients are used to train a BPNNmodel at each scale. The input data for forecasting contain the wavelet coefficients of the air pollutantsconcentrations 1-day in advance, and local meteorological data. The suitable groups of the input variablesare determined by correlation analysis method. At last, the estimated coefficients of the BPNNoutputs for all of the scales are employed to reconstruct the forecasting result through the inverse SWT.The proposed approach is tested using data during 1/1/2011 to 26/12/2011 in Nan'an District ofChongqing, China. The results show that the W-BPNN model has better forecasting performance for thethree air pollutants than mono-BPNN model in terms of the statistics indexes (mean absolute percentageerror, root mean square error and correlation coefficient criteria) and the forecasting accuracy of thenumber of relevant days of individual air quality index.