Coupling bayesian networks with GIS-Based cellular automata for modeling land use change

Authors:
Verda Kocabas;Suzana Dragicevic
Affiliations:
Spatial Analysis and Modeling Laboratory, Department of Geography, Simon Fraser University, Burnaby, BC, Canada;Spatial Analysis and Modeling Laboratory, Department of Geography, Simon Fraser University, Burnaby, BC, Canada
Venue:
GIScience'06 Proceedings of the 4th international conference on Geographic Information Science
Year:
2006

Citing 14
Cited 1

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
Bayesian networks without tears: making Bayesian networks more accessible to the probabilistically unsophisticated

AI Magazine
A Bayesian Method for the Induction of Probabilistic Networks from Data

Machine Learning
Fractal cities: a geometry of form and function

Fractal cities: a geometry of form and function
Real-world applications of Bayesian networks

Communications of the ACM
Learning Bayesian Networks: The Combination of Knowledge and Statistical Data

Machine Learning
A belief network approach to optimization and parameter estimation: application to resource and environmental management

Artificial Intelligence
A tutorial on learning with Bayesian networks

Learning in graphical models
Graphical Models: Foundations of Neural Computation

Graphical Models: Foundations of Neural Computation
Learning Bayesian networks from data: an information-theory based approach

Artificial Intelligence
Application of Bayesian Network Learning Methods to Waste Water Treatment Plants

Applied Intelligence
A Guide to the Literature on Learning Probabilistic Networks from Data

IEEE Transactions on Knowledge and Data Engineering
Learning Bayesian Networks

Learning Bayesian Networks
Operations for learning with graphical models

Journal of Artificial Intelligence Research

Integrating spatial relations into case-based reasoning to solve geographic problems

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Complex systems theory and Cellular Automata (CA) are widely used in geospatial modeling. However, existing models have been limited by challenges such as handling of multiple datasets, parameter definition and the calibration procedures in the modeling process. Bayesian network (BN) formalisms provide an alternative method to address the drawbacks of these existing models. This study proposes a hybrid model that integrates BNs, CA and Geographic Information Systems (GIS) to model land use change. The transition rules of the CA model are generated from a graphical formalism where the key land use drivers are represented by nodes and the dependencies between them are expressed by conditional probabilities extracted from historical spatial datasets. The results indicate that the proposed model is able to realistically simulate and forecast spatio-temporal process of land use change. Further, it forms the basis for new synergies in CA model design that can lead to improved model outcomes.