1. General Model Information

Name: Classification and Regression Tree model

Acronym: CART

Main medium: air+terrestrial
Main subject: biogeochemistry
Organization level: landscape
Type of model: not specified
Main application:
Keywords: GIS, image analysis, remote sensing information, statistical image classification, multiple linear regression


Dave Roberts
Department of Forestry Resources
Utah State University
Logan, UT 84321
Fax : 801-750-1040
email: doug@rsgis.nr.usu.edu



The CART (Classification and Regression Tree) model is a predictive, statistical model used to classify remote sensing information. It employs statistical regression techniques (e.g. stepwise multiple regression) to construct dichotomous decision trees. Training set data are used as input to produce the decision trees. The typical types of training set data used are geology, soils, and topography.

The model produces a classification decision tree on its first pass. For example, it would split all pixels that are classified as vegetation into forest and non-forested pixels. Then, using the training set data, it can split the pixels classified as forest into forest types, such as coniferous and deciduous. On its second pass the model assesses which of the decision tree branches are statistically significant. Those determined to be not significant are "pruned."

Author of the abstract:


II. Technical Information

II.1 Executables:

Operating System(s):

II.2 Source-code:

Programming Language(s):

II.3 Manuals:

II.4 Data:

III. Mathematical Information

III.1 Mathematics

III.2 Quantities

III.2.1 Input

III.2.2 Output

IV. References

V. Further information in the World-Wide-Web

VI. Additional remarks

Global change implications: This model differs from a supervisedclassification of remote sensing data in that the regression trees providea statistical approach to classifying an image. It is used mostly for classifyingvegetation types in a Landsat or AVHRR scene.
Last review of this document by: T. Gabele: 16. 6. 1997 -
Status of the document:
last modified by Tobias Gabele Wed Aug 21 21:44:40 CEST 2002

Go back to Register of Ecological Models (R E M)