Multiobjective Urban Planning Using Genetic Algorithm

Balling, Richard; Taber, John T.; Brown, M. R. W.; Day, Kirsten

doi:10.1061/(asce)0733-9488(1999)125:2(86)

Cited by 125 publications

(63 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the literature of land use optimization, context-based and suitability-related objectives were broadly indicated (Balling et al, 1999;Cao et al, 2012;Chandramouli et al, 2009;Duh & Brown, 2007;Karakostas & Economou, 2014;Liu, Lao, et al, 2012;Liu et al, 2013;Masoomi et al, 2013;Santé-Riveira et al, 2008;Stewart et al, 2004;Wang et al, 2004;Xiao et al, 2002). These functions were often slope, elevation, land price and distance-related factors (e.g.…”

Section: Formulation Of Multi-objective Land Use Optimization Problemmentioning

confidence: 99%

Multi-Objective Land Use Optimization Through Parallel Particle Swarm Algorithm: Case Study Baboldasht District of Isfahan, Iran

Sahebgharani¹

2016

JUEE

View full text Add to dashboard Cite

Abstract:Land use planning seeks to divide land, the most valuable resource in the hands of planners, among different land types. During this process, various conflicting objectives are emerged which land use planners should prepare land use plans satisfying these objectives and deal with a large set of data and variable. For this reason, land use allocation is a multi-objective NP-hard optimization problem which is not solvable by the current exact methods. Therefore, solving land use optimization problem relies on the application of meta-heuristics. In this paper, a novel meta-heuristic named parallel particle swarm is developed to allocate seven land types (residential, commercial, cultural, educational, medical, sportive and green space) to Baboldasht district of Isfahan covered by 200 allocation cells with size 1000 m 2 for maximizing compactness, compatibility and suitability objective functions. Afterwards, the outputs of the new developed algorithm are compared to the outputs of genetic algorithm. The results demonstrated that the parallel particle swarm is better than genetic algorithm in terms of both solution quality (1.35%) and algorithm efficiency (63.7%). The results also showed that the outputs achieved by both algorithms are better than the current state of land use distribution. Thus, the method represented in this paper can be used as a useful tool in the hands of urban planners and decision makers, and supports the land use planning process.

show abstract

Section: Formulation Of Multi-objective Land Use Optimization Problemmentioning

confidence: 99%

Multi-Objective Land Use Optimization Through Parallel Particle Swarm Algorithm: Case Study Baboldasht District of Isfahan, Iran

Sahebgharani¹

2016

JUEE

View full text Add to dashboard Cite

show abstract

“…Balling's [27] Maximin function is used for calculating the fitness values of the genotypes. This function was originally applied for geospatial problems and has been employed in earlier studies involving spatial optimization [15,28].…”

Section: Fitness Calculation and Objectivesmentioning

confidence: 99%

“…Based on the fitness formula described above, the Pareto-optimal plans were selected from a generation based on the fitness values obtained. While dominated plans had a fitness value between 0 and 1, Pareto-optimal plans had fitness values greater than 1 [14,27]. Besides, in this study, a higher value for p is employed.…”

Section: Fitness Calculation and Objectivesmentioning

confidence: 99%

“…Stated otherwise, a plan may outclass the Pareto plan when considering one objective and a different plan may be better with regards to another objective; however, a ''single plan'' must not outdo a Pareto plan in all the objectives considered for the MOO. Balling, Taber, Brown, and Day [27] clearly state that the ''Pareto set is independent of the relative importance of the objectives''. The above discussion evinces that plans do not belong to the Pareto set (non-Pareto plans) are ''dominated'', as a Pareto plan that is better (or that which dominates) has been found.…”

Section: Pareto-optimality and Visualizationmentioning

confidence: 99%

See 1 more Smart Citation

A genetic algorithm based optimization framework to visualize, evaluate, and modify 3D space configurations in Desktop VR

Chandramouli

Bertoline

2014

Int. J. Simul. Multidisci. Des. Optim.

View full text Add to dashboard Cite

-This paper presents the design and implementation of a Desktop VR (Virtual Reality) framework for generating and evaluating Pareto-optimal alternate 3D spatial configurations using GA (genetic algorithms). The 3-tier framework involves the generation of the Pareto-optimal plans using GA which are subsequently visualized first using a Java-based 2D Interface and finally in the form of a 3D VR scene. The search spaces (function domains) are extremely large in today's multifaceted interior design situations, and the optimization procedure involves conflicting objective functions, and limitations in the form of constraint functions. The interior space allocation problem is formulated and implemented as the ''optimal configuration of artifacts''. When using GAs, a group of Pareto-optimal solutions (Pareto set) are available for the planners and decision-makers, wherefrom one solution ought to be picked. Therefore, this study applies a tool to not only visually evaluate the plans, but also to interact with those plans to develop them further if needed. Besides enabling the optimal spatial configuration of the scene elements, this framework also facilitates evaluation and interaction via the 3D VR worlds. The framework aids the proactive exploration, analysis, and finalization of design aspects such as color, size, lighting, etc. of the various elements prior to the actual construction. The results demonstrate the robust performance of the GA and the final 3D VR environment with dynamic interactive capabilities. This final interface facilitates ''GA-Compliant'' transformations and scene modifications thereby facilitating the exploration and examination of alternative scene configurations.

show abstract

“…In this regard, a vast range of broadly documented computational methods and tools has been developed, from linear programming (LP) for one or several objectives [12][13][14][15] to heuristic multiple-objective models, among them evolutionary algorithms (MOEAs) [3,16]. MOEAs do not search for a single solution but rather a set of feasible solutions (the Pareto front) that compensate several frequently opposing objectives, such as competing land uses.…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Spatial Optimization: Sustainable Land Use Allocation at Sub-Regional Scale

García

Rosas²,

García-Ferrer³

et al. 2017

Sustainability

View full text Add to dashboard Cite

Abstract:The rational use of territorial resources is a key factor in achieving sustainability. Spatial planning is an important tool that helps decision makers to achieve sustainability in the long term. This work proposes a multi-objective model for sustainable land use allocation known as MAUSS (Spanish acronym for "Modelo de Asignación de Uso Sostenible de Suelo") The model was applied to the Plains of San Juan, Puebla, Mexico, which is currently undergoing a rapid industrialization process. The main objective of the model is to generate land use allocations that lead to a territorial balance within regions in three main ways by maximizing income, minimizing negative environmental pressure on water and air through specific evaluations of water use and CO 2 emissions, and minimizing food deficit. The non-sorting genetic algorithm II (NSGA-II) is the evolutionary optimization algorithm of MAUSS. NSGA-II has been widely modified through a novel and efficient random initializing operator that enables spatial rationale from the initial solutions, a crossover operator designed to streamline the best genetic information transmission as well as diversity, and two geometric operators, geographic dispersion (GDO) and the proportion (PO), which strengthen spatial rationality. MAUSS provided a more sustainable land use allocation compared to the current land use distribution in terms of higher income, 9% lower global negative pressure on the environment and 5.2% lower food deficit simultaneously.

show abstract

Multiobjective Urban Planning Using Genetic Algorithm

Cited by 125 publications

References 6 publications

Multi-Objective Land Use Optimization Through Parallel Particle Swarm Algorithm: Case Study Baboldasht District of Isfahan, Iran

Multi-Objective Land Use Optimization Through Parallel Particle Swarm Algorithm: Case Study Baboldasht District of Isfahan, Iran

A genetic algorithm based optimization framework to visualize, evaluate, and modify 3D space configurations in Desktop VR

Multi-Objective Spatial Optimization: Sustainable Land Use Allocation at Sub-Regional Scale

Contact Info

Product

Resources

About