A spatial land-use planning support system based on game theory

Abstract Spatial urban land-use planning is a complex process, through which we aim to allocate suitable land-uses while taking into consideration multiple and conflicting objectives and constraints under certain spatial contexts. Landowners should be modeled as players that are able to interact with each other so as to seek their best land-uses while considering multiple objectives and constraints simultaneously. Game theory provides a tool for land-use planners to model and analyze such interactions. In this paper, spatial urban land-use planning is considered as a game to model local competitions between landowners, whose players (i.e. landowners) of which play to pick the most suitable land-use for themselves. The game is defined based on the objectives of consistency, dependency, suitability, compactness of land-uses, and land-use per capita demand. In this paper, three different scenarios are designed for the players. In the first scenario, the players are greedy and only accept the most compatible land-use. In the second scenario, conversely, the players are fully collaborative and care about other players’ payoff. In the third scenario, the players are first greedy, but when they cannot achieve an agreement with other players, they change their attitude to become gradually collaborative for reaching the Nash equilibrium (NE). Furthermore, the dissatisfaction index (DI), which represents the number of unsatisfied landowners with their current land-use, is defined to compare the different scenarios. The proposed model is tested in a district located in District 7 in Tehran (the capital city of Iran) with 2710 parcels. Results of the first scenario showed that, at the beginning of the game, 50 % of the landowners were not satisfied with their current land-uses, but after 50 iterations, about 100 landowners were dissatisfied with their land-use and this scenario was not able to reach the NE. Results of the second scenario indicated that, in order to reach an optimized layout, 325 parcels needed to be changed. Also, after reaching the NE in this scenario, values of the objective functions did not significantly improve. So, lowering the expectations of the players would not lead to appropriate results. The outcomes of the third scenario provided appropriate results, which could be achieved when the expectation levels of the players could be changed during the game. Furthermore, the NE was obtained among the players and the objective functions improved by 20 % on average in comparison with the other scenarios. Moreover, results of the scenarios were compared with the optimized layout obtained by a genetic algorithm (GA) using different parameter values. Results of the comparison also revealed that the urban layouts produced by game theory improved the objective function values obtained by the GA in about 10 % and improved the GA’s running time in more than 85 %, on average in this research.

[1]  Mohammad Karimi,et al.  Simulating urban growth under planning policies through parcel-based cellular automata (ParCA) model , 2016, Int. J. Geogr. Inf. Sci..

[2]  Xia Li,et al.  Modelling sustainable urban development by the integration of constrained cellular automata and GIS , 2000, Int. J. Geogr. Inf. Sci..

[3]  Xia Li,et al.  Cellular automata for simulating land use changes based on support vector machines , 2008, Comput. Geosci..

[4]  Michael Batty,et al.  Spatial multi-objective land use optimization: extensions to the non-dominated sorting genetic algorithm-II , 2011, Int. J. Geogr. Inf. Sci..

[5]  Harry Timmermans,et al.  An Agent-Based Heuristic Method for Generating Land-Use Plans in Urban Planning , 2010 .

[6]  John van Genderen,et al.  Fire Risk Assessment in Dense Urban Areas Using Information Fusion Techniques , 2019, ISPRS Int. J. Geo Inf..

[7]  Tong Xu,et al.  Incorporation of extended neighborhood mechanisms and its impact on urban land-use cellular automata simulations , 2016, Environ. Model. Softw..

[8]  Xiaohu Zhang,et al.  Simulating land-use dynamics under planning policies by integrating artificial immune systems with cellular automata , 2010, Int. J. Geogr. Inf. Sci..

[9]  Zohreh Masoumi,et al.  An improved ant colony optimization-based algorithm for user-centric multi-objective path planning for ubiquitous environments , 2019, Geocarto International.

[10]  T. Stewart,et al.  A multiobjective GIS-based land use planning algorithm , 2014, Comput. Environ. Urban Syst..

[11]  Theo A. Arentze,et al.  An intelligent spatial land use planning support system using socially rational agents , 2017, Int. J. Geogr. Inf. Sci..

[12]  Yasushi Asami,et al.  Optimizing urban land use allocation for planners and real estate developers , 2014, Comput. Environ. Urban Syst..

[13]  Kalyanmoy Deb,et al.  Improving the performance of genetic algorithms for land-use allocation problems , 2018, Int. J. Geogr. Inf. Sci..

[14]  Majid Hamrah,et al.  Allocation of urban land uses by Multi-Objective Particle Swarm Optimization algorithm , 2013, Int. J. Geogr. Inf. Sci..

[15]  Liu Yanfang,et al.  Land use structure optimization under systematic framework , 2002 .

[16]  Feng Liu,et al.  Land-use spatial optimization based on PSO algorithm , 2011, Geo spatial Inf. Sci..

[17]  Ryosuke Shibasaki,et al.  Development of a GIS-based decision support system for assessing land use status , 2004 .

[18]  Mohammad Taleai,et al.  Evaluating the compatibility of multi-functional and intensive urban land uses , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[19]  Peng Xie,et al.  A Local Land Use Competition Cellular Automata Model and Its Application , 2016, ISPRS Int. J. Geo Inf..

[20]  P. Hall,et al.  Urban and Regional Planning , 2019 .

[21]  Yongjiu Feng,et al.  A heuristic cellular automata approach for modelling urban land-use change based on simulated annealing , 2013, Int. J. Geogr. Inf. Sci..

[22]  Wei Tang,et al.  A land-use spatial optimization model based on genetic optimization and game theory , 2015, Comput. Environ. Urban Syst..

[23]  Farshad Hakimpour,et al.  A Parcel-Level Model for Ranking and Allocating Urban Land-Uses , 2017, ISPRS Int. J. Geo Inf..

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

[25]  Carlos A. Coello Coello,et al.  Dynamic urban land-use change management using multi-objective evolutionary algorithms , 2020, Soft Comput..

[26]  Arnold K. Bregt,et al.  Multi-actor-based land use modelling: spatial planning using agents , 2001 .

[27]  Francisco F. Rivera,et al.  High performance genetic algorithm for land use planning , 2013, Comput. Environ. Urban Syst..

[28]  F. Chapin,et al.  Urban Land Use Planning. , 1957 .

[29]  Richard L. Church,et al.  Spatial optimization as a generative technique for sustainable multiobjective land‐use allocation , 2008, Int. J. Geogr. Inf. Sci..

[30]  Suzana Dragicevic,et al.  iCity: A GIS-CA modelling tool for urban planning and decision making , 2007, Environ. Model. Softw..

[31]  A. Mansourian,et al.  Using an Evolutionary Algorithm in Multiobjective Geographic Analysis for Land Use Allocation and Decision Supporting , 2017 .

[32]  Thomas L. Saaty,et al.  Models, Methods, Concepts & Applications of the Analytic Hierarchy Process , 2012 .

[33]  Chris Couch Urban Planning: An Introduction , 2016 .

[34]  Theo A. Arentze,et al.  Socially rational agents in spatial land use planning: A heuristic proposal based negotiation mechanism , 2016, Comput. Environ. Urban Syst..

[35]  Wei Tang,et al.  A game-theory based agent-cellular model for use in urban growth simulation: A case study of the rapidly urbanizing Wuhan area of central China , 2015, Comput. Environ. Urban Syst..

[36]  Azam Afsharnia Assessing the Act of Iran's Supreme Council of Urbanization and Architecture about Land Use per Capita , 2014 .

[37]  Dongmei Chen,et al.  An improved knowledge-informed NSGA-II for multi-objective land allocation (MOLA) , 2018, Geo spatial Inf. Sci..

[38]  Martin J. Osborne,et al.  An Introduction to Game Theory , 2003 .

[39]  Xin Li,et al.  An improved Genetic Algorithm for spatial optimization of multi-objective and multi-site land use allocation , 2016, Comput. Environ. Urban Syst..

[40]  Michael Batty,et al.  Artificial intelligence and smart cities , 2018 .