Training Cellular Automata to Simulate Urban Dynamics: A Computational Study Based on GPGPU and Swarm Intelligence

Previous models for the explanation of settlement processes pay little attention to the interactions between settlement spreading and road networks. On the basis of a dielectric breakdown model in combination with cellular automata, we present a method to steer precisely the generation of settlement structures with regard to their global and local density as well as the size and number of forming clusters. The resulting structures depend on the logic of how the dependence of the settlements and the road network is implemented to the simulation model. After analysing the state of the art we begin with a discussion of the mutual dependence of roads and land development. Next, we elaborate a model that permits the precise control of permeability in the developing structure as well as the settlement density, using the fewest necessary control parameters. On the basis of different characteristic values, possible settlement structures are analysed and compared with each other. Finally, we reflect on the theoretical contribution of the model with regard to the context of urban dynamics.

Download Full-text

Swarm Intelligence for Urban Dynamics Modelling

10.1063/1.3130612 ◽

2009 ◽

Author(s):

Rawan Ghnemat ◽

Cyrille Bertelle ◽

Gérard H. E. Duchamp ◽

Barna Laszlo Iantovics ◽

Enachescu Calin ◽

...

Keyword(s):

Swarm Intelligence ◽

Urban Dynamics ◽

Dynamics Modelling

Download Full-text

Formal analysis in a cellular automata ant model using swarm intelligence in robotics foraging task

2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC) ◽

10.1109/smc.2017.8122876 ◽

2017 ◽

Cited By ~ 1

Author(s):

Danielli A. Lima ◽

Gina M. B. Oliveira

Keyword(s):

Cellular Automata ◽

Swarm Intelligence ◽

Formal Analysis ◽

Foraging Task

Download Full-text

Simulating Urban Dynamics Using Cellular Automata

Artificial Crime Analysis Systems ◽

10.4018/978-1-59904-591-7.ch007 ◽

2011 ◽

pp. 125-139 ◽

Cited By ~ 1

Author(s):

Xia Li

Keyword(s):

Neural Networks ◽

Land Use ◽

Cellular Automata ◽

Land Use Changes ◽

Dynamics Simulation ◽

Spatial Variables ◽

Urban Dynamics ◽

Multiple Land Use ◽

Land Use Dynamics

This chapter introduces the concepts of cellular automata (CA) which have been increasingly used for simulating urban dynamics. Simulation and prediction of urban evolution can provide the useful inputs to crime models. However, calibration of urban cellular automata is crucial for simulating realistic cities. Simulation of multiple land use changes using CA is difficult because numerous spatial variables and parameters have to be utilized. The incorporation of neural networks with CA can alleviate the calibration problems. This chapter illustrates how complex land use dynamics can be simulated by the integration of CA and neural networks.

Download Full-text