Prediction of PM2.5 based on Elman neural network with chaos theory

PM2.5 is difficult to accurately forecast due to the influence of multiple meteorological and pollutant variables in the complex nonlinear dynamic atmosphere system. In this paper, an Elman neural network prediction method based on chaos theory is put forward for the problem. Firstly, the chaotic characteristics of the concentration of the PM2.5 are analyzed and verified from the correlation dimension, the maximum Lyapunov exponent and the Kolmogorov entropy. Then, phase space reconstruction technique of chaotic theory is adopted to reconstruct the phase space of PM2.5 time series. The reconstructed phase space and the future concentration of PM2.5 are taken as the input and output of the Elman neural network with chaos theory (Elman-chaos) respectively. The numerical and experimental analyses show that this method is proportionally superior to that without considering the chaos characteristics and other approaches. The Elman-chaos prediction model has better prediction performance and application value.

[1]  Xin Yin,et al.  Chaotic time series prediction of E-nose sensor drift in embedded phase space , 2013 .

[2]  P. Grassberger,et al.  Characterization of Strange Attractors , 1983 .

[3]  Li Zhemin,et al.  Prediction Model of Weekly Retail Price for Eggs Based on Chaotic Neural Network , 2013 .

[4]  P. Grassberger,et al.  Measuring the Strangeness of Strange Attractors , 1983 .

[5]  P. Grassberger,et al.  Estimation of the Kolmogorov entropy from a chaotic signal , 1983 .

[6]  Lixin Tian,et al.  Chaotic characteristic identification for carbon price and an multi-layer perceptron network prediction model , 2015, Expert Syst. Appl..

[7]  Yan-lin Zhang,et al.  Fine particulate matter (PM2.5) in China at a city level , 2015, Scientific Reports.

[8]  M. Elbayoumi,et al.  Multivariate methods for indoor PM10 and PM2.5 modelling in naturally ventilated schools buildings , 2014 .

[9]  Saeed Zolfaghari,et al.  Chaotic time series prediction with residual analysis method using hybrid Elman-NARX neural networks , 2010, Neurocomputing.

[10]  Qi Li,et al.  Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation , 2015 .

[11]  Koji Zettsu,et al.  Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM2.5 , 2015, Neural Computing and Applications.

[12]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[13]  Mengjie Zhang,et al.  Cooperative coevolution of Elman recurrent neural networks for chaotic time series prediction , 2012, Neurocomputing.

[14]  H. Schuster,et al.  Proper choice of the time delay for the analysis of chaotic time series , 1989 .

[15]  S. Samarasinghe,et al.  Complex time series analysis of PM10 and PM2.5 for a coastal site using artificial neural network modelling and k-means clustering , 2014 .

[16]  Ujjwal Kumar,et al.  ARIMA forecasting of ambient air pollutants (O3, NO, NO2 and CO) , 2010 .

[17]  Wen-Ying Zhang,et al.  Identification of Heart Sounds with Arrhythmia based on Recurrence Quantification Analysis and Kolmogorov Entropy , 2015 .

[18]  James P. Crutchfield,et al.  Geometry from a Time Series , 1980 .

[19]  A. Wolf,et al.  Determining Lyapunov exponents from a time series , 1985 .

[20]  Rong Luo,et al.  An accurate and low-cost PM2.5 estimation method based on Artificial Neural Network , 2015, The 20th Asia and South Pacific Design Automation Conference.

[21]  Ting Wang,et al.  Melt index prediction by aggregated RBF neural networks trained with chaotic theory , 2014, Neurocomputing.

[22]  Hossein Mirzaee,et al.  Long-term prediction of chaotic time series with multi-step prediction horizons by a neural network with Levenberg–Marquardt learning algorithm , 2009 .