|
Activity Number:
|
532
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #304308 |
|
Title:
|
Model Prediction of Ambient Ozone Concentrations
|
|
Author(s):
|
Katerina G. Tsakiri*+ and Igor Zurbenko
|
|
Companies:
|
State University of New York at Albany and State University of New York at Albany
|
|
Address:
|
Department of Mathematics and Statistics, Albany, NY, 12222,
|
|
Keywords:
|
ozone ; solar radiation ; time series prediction ; Kalman filter
|
|
Abstract:
|
We describe techniques for the explanation and prediction of ozone concentrations on example of actual data. A methodology is presented for separating the components in time series of ozone and the atmospheric variables, namely, global components and synoptic scale components. We prove that the components are practically uncorrelated and they have completely different physical background. Solar radiation appears to be the main factor for the explanation of the global component of ozone. The synoptic scale component of ozone can be predicted independently. The results show that the main factors for the prediction of the synoptic scale component of ozone are solar radiation and temperature, when we use the ARMA model and the Kalman filter. The investigation of the highest R2 is presented for both models and appears to be 53%, which is essentially higher compare with single scaled models.
|
