摘要：With the development of science and technology, Industry, transportation and other industries used to discharge a large number of pollutants into the atmosphere, which results in air pollution. When air pollution become serious, it will do great harm to human health. High-precision Air Quality Index(AQI) prediction is as important as weather prediction. People could arrange traveling and their life according to the highly precise prediction results, so as to better protect their own health. Considering a lot of complex factors, we choose several potential meteorological factors and historical data to precisely forecast AQI. The principal component analysis (PCA) is introduced in our method to conduct dimension reduction on nine meteorological factors, in order to reduce noise of data and the complexity of the model calculation, which improves the accuracy of AQI prediction as a result. Then the data of meteorological factors after PCA and historical AQI are input into the multi-step prediction model based on LSSVM to train and refine it. Finally, we set up the experiment with data of meteorological factors and AQI. Experimental results show that the method proposed in this paper has better prediction accuracy over classical ARIMA method and has better generalization than ARIMA method as well.
