论文信息 - Neural Network Model for Maximum Ozone Concentration Prediction

Neural Network Model for Maximum Ozone Concentration Prediction

A neural network dynamic model was used for predicting maximum ozone (O3) concentration at Santiago de Chile. Learning and test data were collected during summer and springtime periods of 1990, 1992 and 1993. A neural network having O3 t, Tt+1 (maximum air temperature) and Tt as inputs for predicting O3 t+1 was chosen because of its low test error. This neural network model greatly reduces the error coming from a pure persistence model when applied to the generalization set of data (1994). Long-term predictions results confirm the good concordance obtained between the observed and forecasted values thus showing the adequacy of neural networks to model the dynamics of this complex environmental phenomena.

[1] Pierre Roussel-Ragot,et al. Neural Networks and Nonlinear Adaptive Filtering: Unifying Concepts and New Algorithms , 1993, Neural Computation.

[2] K. Wilson,et al. Linear stochastic models for forecasting daily maxima and hourly concentrations of air pollutants , 1975 .

[3] Lennart Ljung,et al. Nonlinear Black Box Modeling in System Identification , 1995 .

[4] E. Clothiaux,et al. Neural Networks and Their Applications , 1994 .

[5] Lennart Ljung,et al. Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[6] Scott M. Robeson,et al. Evaluation and comparison of statistical forecast models for daily maximum ozone concentrations , 1990 .

[7] Beverly E. Tilton,et al. Health effects of tropospheric ozone , 1989 .

[8] Jules Thibault,et al. Neural network models for final process time determination in fermented milk production , 1994 .

[9] M. Lippmann. Health effects of ozone. A critical review. , 1989, JAPCA.

[10] P. Werbos,et al. Long-term predictions of chemical processes using recurrent neural networks: a parallel training approach , 1992 .

[11] A. Lloyd,et al. An updated chemical mechanism for hydrocarbon/NOx/SO2 photooxidations suitable for inclusion in atmospheric simulation models , 1982 .