Home

Proceedings of the International Academy of Ecology and Environmental Sciences, 2012, 2(2): 53-69
[XML] [EndNote Tagged] [BibTex] [ Full PDF (192K)] [Comment Article]

Article

An integrated parcel-based land use change model using cellular automata and decision tree

Florencio Ballestores Jr. 1, Zeyuan Qiu 2
1Department of Chemical Engineering, University of Philippine Diliman, Quezon City, Philippines
2Environmental Policy Studies, New Jersey Institute of Technology, University Heights, Newark, New Jersey 07102, USA

Received 6 March 2012;Accepted 10 April 2012;Published online 5 June 2012
IAEES

Abstract
Ecological changes are driven by changes in land use. Modeling land use change is an essential step to adaptively manage ecosystem to mitigate the negative impacts of such ecological changes. This study developed a parcel-based spatial land use change prediction model by coupling a couple of machine learning and interpretation algorithms: cellular automata and decision tree. The model was developed and validated using the historical land use data in Hunterdon County of New Jersey in the United States. Specifically, the data on historical land uses and various driving factors that affect land use changes for Hunterdon County were collected and processed using a Geographic Information System. A set of transition rules illustrating the land use change processes during the period 1986-1995 were developed using decision tree J48 Classifier. The derived transition rules were applied to the 1995 land use data in a cellular automata model Agent Analyst to predict future spatial land use pattern, which were then validated by the actual land use in 2002. The decision tree-based cellular automata model has reasonable overall accuracy of 84.46 percent in predicting land use changes and the Cohen's Kappa Index is 0.644. The model shows much higher capacity in predicting the quantitative changes than the locational changes in land use. Sensitivity analysis indicates that simply changing the size of neighborhood has slight impacts on the simulation results, but insignificant impacts on the model accuracy.

Keywords land use change;cellular automata;decision tree;parcel;geographic information system;J48 Classifier;Agent Analyst.


International Academy of Ecology and Environmental Sciences. E-mail: office@iaees.org
Copyright © 2009-2024 International Academy of Ecology and Environmental Sciences. All rights reserved.
Web administrator: office@iaees.org, website@iaees.org; Last modified: 2024/4/19


Translate page to: