Modeling urban expansion by using variable weights logistic cellular automata

a case study of Nanjing, China

Bangrong Shu*, Martha M. Bakker, Honghui Zhang, Yongle Li, Wei Qin, Gerrit J. Carsjens

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

16 Citations (Scopus)

Abstract

Simulation models based on cellular automata (CA) are widely used for understanding and simulating complex urban expansion process. Among these models, logistic CA (LCA) is commonly adopted. However, the performance of LCA models is often limited because the fixed coefficients obtained from binary logistic regression do not reflect the spatiotemporal heterogeneity of transition rules. Therefore, we propose a variable weights LCA (VW-LCA) model with dynamic transition rules. The regression coefficients in this VW-LCA model are based on VW by incorporating a genetic algorithm in a conventional LCA. The VW-LCA model and the conventional LCA model were both used to simulate urban expansion in Nanjing, China. The models were calibrated with data for the period 2000–2007 and validated for the period 2007–2013. The results showed that the VW-LCA model performed better than the LCA model in terms of both visual inspection and key indicators. For example, kappa, accuracy of urban land and figure of merit for the simulation results of 2013 increased by 3.26%, 2.96% and 4.44%, respectively. The VW-LCA model performs relatively better compared with other improved LCA models that are suggested in literature.
Original languageEnglish
Pages (from-to)1314-1333
JournalInternational Journal of Geographical Information Science
Volume31
Issue number7
DOIs
Publication statusPublished - 2017

Fingerprint

cellular automaton
Cellular automata
Logistics
logistics
China
modeling
regression
simulation model
genetic algorithm
simulation
Genetic algorithms
Inspection

Keywords

  • genetic algorithm
  • logistic cellular automata
  • Nanjing city
  • Urban expansion simulation
  • variable weights

Cite this

@article{c046607c91554e67851a3b0a26e06cb8,
title = "Modeling urban expansion by using variable weights logistic cellular automata: a case study of Nanjing, China",
abstract = "Simulation models based on cellular automata (CA) are widely used for understanding and simulating complex urban expansion process. Among these models, logistic CA (LCA) is commonly adopted. However, the performance of LCA models is often limited because the fixed coefficients obtained from binary logistic regression do not reflect the spatiotemporal heterogeneity of transition rules. Therefore, we propose a variable weights LCA (VW-LCA) model with dynamic transition rules. The regression coefficients in this VW-LCA model are based on VW by incorporating a genetic algorithm in a conventional LCA. The VW-LCA model and the conventional LCA model were both used to simulate urban expansion in Nanjing, China. The models were calibrated with data for the period 2000–2007 and validated for the period 2007–2013. The results showed that the VW-LCA model performed better than the LCA model in terms of both visual inspection and key indicators. For example, kappa, accuracy of urban land and figure of merit for the simulation results of 2013 increased by 3.26{\%}, 2.96{\%} and 4.44{\%}, respectively. The VW-LCA model performs relatively better compared with other improved LCA models that are suggested in literature.",
keywords = "genetic algorithm, logistic cellular automata, Nanjing city, Urban expansion simulation, variable weights",
author = "Bangrong Shu and Bakker, {Martha M.} and Honghui Zhang and Yongle Li and Wei Qin and Carsjens, {Gerrit J.}",
year = "2017",
doi = "10.1080/13658816.2017.1283505",
language = "English",
volume = "31",
pages = "1314--1333",
journal = "International Journal of Geographical Information Science",
issn = "1365-8816",
publisher = "Taylor & Francis",
number = "7",

}

Modeling urban expansion by using variable weights logistic cellular automata : a case study of Nanjing, China. / Shu, Bangrong; Bakker, Martha M.; Zhang, Honghui; Li, Yongle; Qin, Wei; Carsjens, Gerrit J.

In: International Journal of Geographical Information Science, Vol. 31, No. 7, 2017, p. 1314-1333.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Modeling urban expansion by using variable weights logistic cellular automata

T2 - a case study of Nanjing, China

AU - Shu, Bangrong

AU - Bakker, Martha M.

AU - Zhang, Honghui

AU - Li, Yongle

AU - Qin, Wei

AU - Carsjens, Gerrit J.

PY - 2017

Y1 - 2017

N2 - Simulation models based on cellular automata (CA) are widely used for understanding and simulating complex urban expansion process. Among these models, logistic CA (LCA) is commonly adopted. However, the performance of LCA models is often limited because the fixed coefficients obtained from binary logistic regression do not reflect the spatiotemporal heterogeneity of transition rules. Therefore, we propose a variable weights LCA (VW-LCA) model with dynamic transition rules. The regression coefficients in this VW-LCA model are based on VW by incorporating a genetic algorithm in a conventional LCA. The VW-LCA model and the conventional LCA model were both used to simulate urban expansion in Nanjing, China. The models were calibrated with data for the period 2000–2007 and validated for the period 2007–2013. The results showed that the VW-LCA model performed better than the LCA model in terms of both visual inspection and key indicators. For example, kappa, accuracy of urban land and figure of merit for the simulation results of 2013 increased by 3.26%, 2.96% and 4.44%, respectively. The VW-LCA model performs relatively better compared with other improved LCA models that are suggested in literature.

AB - Simulation models based on cellular automata (CA) are widely used for understanding and simulating complex urban expansion process. Among these models, logistic CA (LCA) is commonly adopted. However, the performance of LCA models is often limited because the fixed coefficients obtained from binary logistic regression do not reflect the spatiotemporal heterogeneity of transition rules. Therefore, we propose a variable weights LCA (VW-LCA) model with dynamic transition rules. The regression coefficients in this VW-LCA model are based on VW by incorporating a genetic algorithm in a conventional LCA. The VW-LCA model and the conventional LCA model were both used to simulate urban expansion in Nanjing, China. The models were calibrated with data for the period 2000–2007 and validated for the period 2007–2013. The results showed that the VW-LCA model performed better than the LCA model in terms of both visual inspection and key indicators. For example, kappa, accuracy of urban land and figure of merit for the simulation results of 2013 increased by 3.26%, 2.96% and 4.44%, respectively. The VW-LCA model performs relatively better compared with other improved LCA models that are suggested in literature.

KW - genetic algorithm

KW - logistic cellular automata

KW - Nanjing city

KW - Urban expansion simulation

KW - variable weights

U2 - 10.1080/13658816.2017.1283505

DO - 10.1080/13658816.2017.1283505

M3 - Article

VL - 31

SP - 1314

EP - 1333

JO - International Journal of Geographical Information Science

JF - International Journal of Geographical Information Science

SN - 1365-8816

IS - 7

ER -