Combining classification and regression trees and the neuro-fuzzy inference system for environmental data modeling

Author

Burrows, William R.

Author_Institution

Meteorol. Res. Branch, Atmos. Environ. Service, Downsview, Ont., Canada

fYear

1999

fDate

36342

Firstpage

695

Lastpage

699

Abstract

A procedure is presented for dynamic statistical modeling of predictands with nonlinear predictand-predictor relationships when there are many potential predictors. Classification and regression trees (CART) are used for predictor selection and data stratification. The CART output is suitable for piecewise-continuous predictands. Using predictors selected by CART, a neuro-fuzzy inference system (NFIS) algorithm produces an output model for continuous predictands. An application to modeling ground-level ozone is discussed

Keywords

air pollution; data models; environmental science computing; forecasting theory; fuzzy neural nets; inference mechanisms; ozone; pattern classification; piecewise polynomial techniques; statistical analysis; trees (mathematics); CART; O₃; classification trees; data stratification; dynamic statistical modeling; environmental data modeling; ground-level O₃ modelling; neuro-fuzzy inference system; nonlinear predictand-predictor relationships; output model; piecewise-continuous predictands; predictor selection; regression trees; Application software; Atmospheric modeling; Classification tree analysis; Demand forecasting; Inference algorithms; Meteorology; Predictive models; Regression tree analysis; Weather forecasting; Wind forecasting;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Information Processing Society, 1999. NAFIPS. 18th International Conference of the North American

Conference_Location

New York, NY

Print_ISBN

0-7803-5211-4

Type

conf

DOI

10.1109/NAFIPS.1999.781783

Filename

781783