Prediction of Ozone Concentration in Semi-Arid Areas of China Using a Novel Hybrid Model

The semi-arid regions of China support delicately balanced ecosystems that are likely to be significantly affected by small changes in the level of atmospheric ozone. To predict ozone concentrations in such areas, this paper proposes a new hybrid forecasting model called an ARMT-CPSO-BP neural network, which is based on the association rule mining technique (ARMT), a chaotic particle swarm optimization algorithm (CPSO) and a back-propagation (BP) neural network (CPSO-BP neural network). This paper first uses the ARMT to find correlations between meteorological variables and ozone concentrations. The significant correlation coefficients are then fed into the CPSO-BP neural network to obtain a prediction. Finally, the predicted results are compared with the results obtained from the BP neural network and the regression model. The comparison shows that the proposed hybrid model is superior to both the BP neural network and the regression model. The hybrid model reduces the square root mean square error (RMSE) by 31.6% compared to the BP model and by 23.8% compared to the regression model. The hybrid model is promising for forecasting ozone concentration in arid and semi-arid areas.

[1]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[2]  Zhaozhong Feng,et al.  Assessing the impacts of current and future concentrations of surface ozone on crop yield with meta-analysis , 2009 .

[3]  Lixiang Li,et al.  CHAOTIC PARTICLE SWARM OPTIMIZATION FOR ECONOMIC DISPATCH CONSIDERING THE GENERATOR CONSTRAINTS , 2007 .

[4]  D. Jaffe,et al.  Increase in surface ozone at rural sites in the western US , 2005 .

[5]  WangYi-Hsien.  Nonlinear neural network forecasting model for stock index option price , 2009 .

[6]  Yudong Zhang,et al.  Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network , 2009, Expert Syst. Appl..

[7]  Alicia Troncoso Lora,et al.  Mining quantitative association rules based on evolutionary computation and its application to atmospheric pollution , 2010, Integr. Comput. Aided Eng..

[8]  Kun-Lin Hsieh,et al.  Model construction and parameter effect for TFT-LCD process based on yield analysis by using ANNs and stepwise regression , 2008, Expert Syst. Appl..

[9]  A. Elkamela,et al.  Measurement and prediction of ozone levels around a heavily industrialized area : a neural network approach , 2000 .

[10]  Hsin-Chung Lu,et al.  Prediction of daily maximum ozone concentrations from meteorological conditions using a two-stage neural network , 2006 .

[11]  Lei Zhang,et al.  An overview of the Semi-arid Climate and Environment Research Observatory over the Loess Plateau , 2008 .

[12]  Jun Cai,et al.  Multi-fault classification based on support vector machine trained by chaos particle swarm optimization , 2010, Knowl. Based Syst..

[13]  N. MacDonald.  Nonlinear dynamics , 1980, Nature.

[14]  R. Bhavani,et al.  PSO trained ANN-based differential protection scheme for power transformers , 2008, Neurocomputing.

[15]  Alicia Troncoso Lora,et al.  An evolutionary algorithm to discover quantitative association rules in multidimensional time series , 2011, Soft Comput..

[16]  Jorge Reyes,et al.  An integrated neural network model for PM10 forecasting , 2006 .

[17]  Frédérik Meleux,et al.  Increase in summer European ozone amounts due to climate change , 2006 .

[18]  H. Tanimoto.  Increase in springtime tropospheric ozone at a mountainous site in Japan for the period 1998–2006 , 2009 .

[19]  F. Méndez,et al.  Simplified model for the prediction of ozone generation in polluted urban areas with continuous precursor species emissions , 1999 .

[20]  B. Clarke,et al.  An assessment of the impact of ambient ozone on field-grown crops in New Jersey using the EDU method: part 1-white potato (Solanum tuberosum). , 1990, Environmental pollution.

[21]  Joseph Rynkiewicz,et al.  A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions , 2007, Environ. Model. Softw..

[22]  Yi-Hsien Wang,et al.  Nonlinear neural network forecasting model for stock index option price: Hybrid GJR-GARCH approach , 2009, Expert Syst. Appl..

[23]  J. Andrew Ware,et al.  Residential property price time series forecasting with neural networks , 2002, Knowl. Based Syst..

[24]  Victor R. Prybutok,et al.  Comparison of neural network models with ARIMA and regression models for prediction of Houston's daily maximum ozone concentrations , 2000, Eur. J. Oper. Res..

[25]  G. Ball,et al.  An international cooperative programme indicates the widespread occurrence of ozone injury on crops , 2000 .

[26]  R. E. Abdel-Aal,et al.  Modeling and forecasting the mean hourly wind speed time series using GMDH-based abductive networks , 2009 .

[27]  Li Xiang,et al.  A New ANN Optimized By Improved PSO Algorithm Combined With Chaos And Its Application In Short-term Load Forecasting , 2006, 2006 International Conference on Computational Intelligence and Security.

[28]  Bo Liu,et al.  Improved particle swarm optimization combined with chaos , 2005 .

[29]  S. Islam,et al.  Nonlinear dynamics of hourly ozone concentrations. nonparametric short term prediction , 1998 .