An Optimised Cellular Automata Model Based on Adaptive Genetic Algorithm for Urban Growth Simulation
This paper presents an improved cellular automata (CA) model optimised using an adaptive genetic algorithm (AGA) to simulate the spatio-temporal processes of urban growth. The AGA technique was used to optimise the transition rules of the CA model defined through conventional logistic regression approach, resulting in higher simulation efficiency and improved results. Application of the AGA based CA model in Shanghais Jiading District, Eastern China demonstrates that the model was able to generate reasonable representation of urban growth even with limited input data in defining its transition rules. The research shows that AGA technique can be integrated within a conventional CA based urban simulation model to improve human understanding on urban dynamics.
KeywordsCellular Automaton Cellular Automaton Urban Growth Transition Rule Urban State
This study was supported by the Innovation Program of Shanghai Municipal Education Commission (project no. 11YZ154), the Special Research Fund for Selected Outstanding Young University Scholars in Shanghai (project no. SSC09018), and the University of Queensland New Staff Research Start-up Fund (project no. 601871).
- Espinoza F, Minsker BS, Goldberg D (2001) A self-adaptive hybrid genetic algorithm. In Spector L, Goodman E, Wu A, Langdon WB, Voigt H-M, Gen M, Sen S, Dorigo M, Pezeshk S, Garzon M, Burke E (Eds.) GECCO 2001: Proceedings of the Genetic and Evolutionary Computation Conference. Morgan Kaufmann Publishers, San FranciscoGoogle Scholar
- Huang MX, Gong JH, Zhou S, Liu CB, Zhang LH (2007) Genetic algorithm-based decision tree classifier for remote sensing mapping with SPOT-5 data in the Hongshimao watershed of the loess plateau, China. Neural Comput Appl 6(6):513–517Google Scholar
- Kee E, Airey S, Cye W (2001) An adaptive genetic algorithm. In Spector L, Goodman E, Wu A, Langdon WB, Voigt H-M, Gen M, Sen S, Dorigo M, Pezeshk S, Garzon M, Burke E (Eds.) GECCO 2001: Proceedings of the Genetic and Evolutionary Computation Conference. Morgan Kaufmann Publishers, San Francisco pp 391–397Google Scholar
- Li X, Yeh AGO (2002b) Urban simulation using principal components analysis and cellular automata for land-use planning. Photogramm Eng Rem Sens 68(4):341–351Google Scholar