The Use of Particle Swarm Optimization for a Vector Cellular Automata Model of Land Use Change (Short Paper)

Cellular automata (CA) is an important area of research in GIScience, with recent research developing vector-based models in addition to the traditional raster data formats. One active area of research is the calibration of transition rules, particularly when applied to vector CA. Here we evaluate a particle swarm optimization (PSO) process to calibrate a vector CA model of land use change for a sub-region of Ipswich in Queensland, Australia, for the period 1999-2016. We compare the results with those for a raster CA of the same dataset. The spatial indices of the vector PSO-CA model exceed that of the raster model, with spatial accuracies being 82.45% and 76.47%, respectively. In addition, the vector PSO-CA model achieved a higher kappa coefficient. Vector-based PSO-CA model can be used for the exploration of urbanization process and provide a better understanding of land use change. 2012 ACM Subject Classification Computing methodologies → Modeling methodologies

[1]  Richard E. Klosterman,et al.  The What If? Collaborative Planning Support System , 1999 .

[2]  Lin Liu,et al.  A bottom‐up approach to discover transition rules of cellular automata using ant intelligence , 2008, Int. J. Geogr. Inf. Sci..

[3]  Suzana Dragicevic,et al.  Assessing cellular automata model behaviour using a sensitivity analysis approach , 2006, Comput. Environ. Urban Syst..

[4]  Fang Wang,et al.  Implementation of a dynamic neighborhood in a land-use vector-based cellular automata model , 2009, Comput. Environ. Urban Syst..

[5]  A. Martín del Rey,et al.  Modelling forest fire spread using hexagonal cellular automata , 2007 .

[6]  Min Cao,et al.  A new discovery of transition rules for cellular automata by using cuckoo search algorithm , 2015, Int. J. Geogr. Inf. Sci..

[7]  A. Schadschneider,et al.  Metastable states in cellular automata for traffic flow , 1998, cond-mat/9804170.

[8]  Anthony Gar-On Yeh,et al.  Neural-network-based cellular automata for simulating multiple land use changes using GIS , 2002, Int. J. Geogr. Inf. Sci..

[9]  Peter Nijkamp,et al.  A Multi-Scenario Forecast of Urban Change: A Study on Urban Growth in the Algarve , 2011 .

[10]  R. Stimson,et al.  A Geographically Weighted Regression Method to Spatially Disaggregate Regional Employment Forecasts for South East Queensland , 2009 .

[11]  Yan Liu,et al.  Modeling dynamic urban growth using cellular automata and particle swarm optimization rules , 2011 .

[12]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[13]  Xuezhi Feng,et al.  Accuracy assessment of seven global land cover datasets over China , 2017 .

[14]  Fang Wang,et al.  Identifying dominant factors for the calibration of a land-use cellular automata model using Rough Set Theory , 2011, Comput. Environ. Urban Syst..

[15]  Ruth J. Doran,et al.  Simulating the spatial dynamics of foot and mouth disease outbreaks in feral pigs and livestock in Queensland, Australia, using a susceptible-infected-recovered cellular automata model. , 2005, Preventive veterinary medicine.

[16]  Yongjiu Feng,et al.  Spatially-Explicit Simulation of Urban Growth through Self-Adaptive Genetic Algorithm and Cellular Automata Modelling , 2014 .

[17]  Michael Batty,et al.  From Cells to Cities , 1994 .

[18]  Yongjiu Feng,et al.  A Cellular Automata Model Based on Nonlinear Kernel Principal Component Analysis for Urban Growth Simulation , 2013 .

[19]  Jacob Cohen,et al.  Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. , 1968 .

[20]  Fang Wang,et al.  A Patch‐based Cellular Automaton for Simulating Land‐use Changes at Fine Spatial Resolution , 2013, Trans. GIS.

[21]  Alan T. Murray,et al.  Monitoring Growth in Rapidly Urbanizing Areas Using Remotely Sensed Data , 2000 .