Improving the performance of genetic algorithms for land-use allocation problems

ABSTRACT Multi-objective optimization can be used to solve land-use allocation problems involving multiple conflicting objectives. In this paper, we show how genetic algorithms can be improved in order to effectively and efficiently solve multi-objective land-use allocation problems. Our focus lies on improving crossover and mutation operators of the genetic algorithms. We tested a range of different approaches either based on the literature or proposed for the first time. We applied them to a land-use allocation problem in Switzerland including two conflicting objectives: ensuring compact urban development and reducing the loss of agricultural productivity. We compared all approaches by calculating hypervolumes and by analysing the spread of the produced non-dominated fronts. Our results suggest that a combination of different mutation operators, of which at least one includes spatial heuristics, can help to find well-distributed fronts of non-dominated solutions. The tested modified crossover operators did not significantly improve the results. These findings provide a benchmark for multi-objective optimization of land-use allocation problems with promising prospectives for solving complex spatial planning problems.

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

[2]  Cheng-Min Feng,et al.  Using a genetic algorithm to generate alternative sketch maps for urban planning , 1999 .

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

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

[5]  David W. Coit,et al.  Multi-objective optimization using genetic algorithms: A tutorial , 2006, Reliab. Eng. Syst. Saf..

[6]  Theodor J. Stewart,et al.  A genetic algorithm approach to multiobjective land use planning , 2004, Comput. Oper. Res..

[7]  Erik D. Goodman,et al.  Triple Bottomline Many‐Objective‐Based Decision Making for a Land Use Management Problem , 2015 .

[8]  Xiaoping Liu,et al.  A multi-type ant colony optimization (MACO) method for optimal land use allocation in large areas , 2012, Int. J. Geogr. Inf. Sci..

[9]  Spiros M. Karakostas,et al.  Land-use planning via enhanced multi-objective evolutionary algorithms: optimizing the land value of major Greenfield initiatives , 2016 .

[10]  Shaowen Wang,et al.  Sustainable land use optimization using Boundary-based Fast Genetic Algorithm , 2012, Comput. Environ. Urban Syst..

[11]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[12]  Yourim Yoon,et al.  A Mathematical Design of Genetic Operators on , 2014 .

[13]  H. Rittel,et al.  Dilemmas in a general theory of planning , 1973 .

[14]  M. Artmann.  Managing urban soil sealing in Munich and Leipzig (Germany)—From a wicked problem to clumsy solutions , 2015 .

[15]  Neil Debbage,et al.  The urban heat island effect and city contiguity , 2015, Comput. Environ. Urban Syst..

[16]  Carlos M. Fonseca,et al.  Multi-objective evolutionary algorithm for land-use management problem , 2007 .

[17]  Ron Janssen,et al.  Evaluating Spatial Design Techniques for Solving Land-use Allocation Problems , 2005 .

[18]  Gary B. Lamont,et al.  Evolutionary Algorithms for Solving Multi-Objective Problems , 2002, Genetic Algorithms and Evolutionary Computation.

[19]  Thomas Hartmann,et al.  Wicked problems and clumsy solutions: Planning as expectation management , 2012 .

[20]  Xu Sun,et al.  An improved artificial bee colony algorithm for optimal land-use allocation , 2015, Int. J. Geogr. Inf. Sci..

[21]  Abbas Alimohammadi,et al.  Spatial Multi-Objective Optimization Approach for Land Use Allocation Using NSGA-II , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

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

[23]  Susan Craw,et al.  Applying Genetic Algorithms to Multi-Objective Land Use Planning , 2000, GECCO.

[24]  J. Farley,et al.  WICKED PROBLEMS , 2007 .

[25]  Dimitrios Economou,et al.  Enhanced multi-objective optimization algorithm for renewable energy sources: optimal spatial development of wind farms , 2014, Int. J. Geogr. Inf. Sci..

[26]  Richard J. Balling,et al.  Multiobjective Urban Planning Using Genetic Algorithm , 1999 .

[27]  Kalyanmoy Deb,et al.  A review of hybrid evolutionary multiple criteria decision making methods , 2014, 2014 IEEE Congress on Evolutionary Computation (CEC).

[28]  Yourim Yoon,et al.  A Mathematical Design of Genetic Operators on GL n ( Z 2 ) , 2015 .

[29]  Martin Volk,et al.  Optimization-based trade-off analysis of biodiesel crop production for managing an agricultural catchment , 2013, Environ. Model. Softw..

[30]  Warren E. Walker,et al.  Adapt or Perish: A Review of Planning Approaches for Adaptation under Deep Uncertainty , 2013 .

[31]  Ramanathan Sugumaran,et al.  Spatial Decision Support Systems: Principles and Practices , 2010 .

[32]  R. K. Ursem.  Multi-objective Optimization using Evolutionary Algorithms , 2009 .

[33]  Kaveh Khalili Damghani,et al.  Solving land-use suitability analysis and planning problem by a hybrid meta-heuristic algorithm , 2014, Int. J. Geogr. Inf. Sci..

[34]  Zhenhua Li,et al.  Learning building block structure from crossover failure , 2007, GECCO '07.

[35]  D. Caparros-Midwood,et al.  Optimised spatial planning to meet long term urban sustainability objectives , 2015, Comput. Environ. Urban Syst..

[36]  Spiros M. Karakostas,et al.  Multi-objective optimization in spatial planning: Improving the effectiveness of multi-objective evolutionary algorithms (non-dominated sorting genetic algorithm II) , 2015 .

[37]  Ron Janssen,et al.  Multiobjective Decision Support for Land-Use Planning , 2008 .

[38]  Eckart Zitzler,et al.  Evolutionary algorithms for multiobjective optimization: methods and applications , 1999 .

[39]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[40]  G. Heuvelink,et al.  Using Linear Integer Programming for Multi-Site Land-Use Allocation , 2003 .

[41]  Marc Parizeau,et al.  DEAP: evolutionary algorithms made easy , 2012, J. Mach. Learn. Res..

[42]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[43]  Claus Rinner,et al.  Advances in Geographic Information Science , 2015 .

[44]  Erik D. Goodman,et al.  Reducing the loss of agricultural productivity due to compact urban development in municipalities of Switzerland , 2017, Comput. Environ. Urban Syst..

[45]  Ralf Seppelt,et al.  Evaluating cost-effectiveness of conservation management actions in an agricultural landscape on a regional scale , 2007 .

[46]  Warren E. Walker,et al.  Coping with the Wickedness of Public Policy Problems: Approaches for Decision Making under Deep Uncertainty , 2016 .

[47]  Xinyue Ye,et al.  Coarse-grained parallel genetic algorithm applied to a vector based land use allocation optimization problem: the case study of Tongzhou Newtown, Beijing, China , 2013, Stochastic Environmental Research and Risk Assessment.

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

[49]  Jennifer Ryan,et al.  A Two-Dimensional Genetic Algorithm for the Ising Problem , 1991, Complex Syst..

[50]  Jingwei Hou,et al.  Optimal spatial land-use allocation for limited development ecological zones based on the geographic information system and a genetic ant colony algorithm , 2015, Int. J. Geogr. Inf. Sci..

[51]  Patrick M. Reed,et al.  Borg: An Auto-Adaptive Many-Objective Evolutionary Computing Framework , 2013, Evolutionary Computation.

[52]  M. Armstrong,et al.  Exploring the Geographic Consequences of Public Policies Using Evolutionary Algorithms , 2004, Annals of the Association of American Geographers.

[53]  Kalyanmoy Deb,et al.  Meaningful representation and recombination of variable length genomes , 2012, GECCO '12.

[54]  Marco Laumanns,et al.  A Tutorial on Evolutionary Multiobjective Optimization , 2004, Metaheuristics for Multiobjective Optimisation.

[55]  Qingfu Zhang,et al.  Multiobjective evolutionary algorithms: A survey of the state of the art , 2011, Swarm Evol. Comput..

[56]  Lothar Thiele,et al.  Comparison of Multiobjective Evolutionary Algorithms: Empirical Results , 2000, Evolutionary Computation.

[57]  Marjan Mernik,et al.  Exploration and exploitation in evolutionary algorithms: A survey , 2013, CSUR.

[58]  Mark A. Friedl,et al.  Urbanization and the loss of prime farmland: a case study in the Calgary–Edmonton corridor of Alberta , 2015, Regional Environmental Change.

[59]  Fred Toppen,et al.  Planning Support Systems for Sustainable Urban Development , 2013 .

[60]  Xiaoping Liu,et al.  International Journal of Geographical Information Science an Improved Artificial Immune System for Seeking the Pareto Front of Land-use Allocation Problem in Large Areas an Improved Artificial Immune System for Seeking the Pareto Front of Land-use Allocation Problem in Large Areas , 2022 .

[61]  William F. Punch,et al.  Crossover gene selection by spatial location , 2006, GECCO '06.

[62]  Kalyanmoy Deb,et al.  Multi-objective Genetic Algorithms: Problem Difficulties and Construction of Test Problems , 1999, Evolutionary Computation.

[63]  Inés Santé-Riveira,et al.  Algorithm based on simulated annealing for land-use allocation , 2008, Comput. Geosci..

[64]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[65]  Bahram Saghafian,et al.  Hydrology and Earth System Sciences Multi-objective Optimization for Combined Quality–quantity Urban Runoff Control , 2022 .

[66]  Kalyanmoy Deb,et al.  Approximating a multi-dimensional Pareto front for a land use management problem: A modified MOEA with an epigenetic silencing metaphor , 2012, 2012 IEEE Congress on Evolutionary Computation.