基于二层分解技术和改进极限学习机模型的PM2.5浓度预测研究.

Accurate PM2.5 concentration forecasting is crucial for protecting public health and improving air quality. However, the randomness, non-linearity and non-stationarity of PM2.5 concentration series increase the difficulty in PM2.5 concentration forecasting. In order to improve the accuracy of PM2.5 concentration forecasting, this paper proposes a novel hybrid model based on two-layer decomposition technique integrated fast ensemble empirical mode decomposition (FEEMD), variational mode decomposition (VMD) and extreme learning machine (ELM) model optimized by differential evolution (DE) algorithm. To testify the validity of the proposed model, the PM2.5 concentration series of Beijing and Sliijiazhuang are taken as the test cases t o conduct empirical study. Based on the experiment results, the following two conclusions can be obtained: 1) compared with single decomposition technique, the proposed two-layer decomposition technique can efficiently decrease the characteristics of 11011-linearity and non-stationarity of PM2.5 concentration series; 2) the proposed FEEMD-VMD-DE-ELM model can precisely forecast the PM2.5 concentration. [ABSTRACT FROM AUTHOR]