Document Type : Original Research Paper
Author
Department of Transportation Engineering, Isfahan University of Technology, Isfahan 84156-83111, Iran
Abstract
Background and Objectives: Population growth in human settlements leads to an increase in land use demand. Consequently, optimal urban land use planning is critical for planners and decision-makers. Given that land use allocation involves multiple objectives and a large set of data and variables, solving this problem requires developing decision support systems (DSSs) and applying meta-heuristic algorithms.
In this paper, a DSS equipped with an optimization method (i.e., Ant Colony Optimization algorithm) is developed to solve the land use allocation problem. The study aims to design a graphical user interface (GUI) to facilitate the algorithm implementation process and apply it to a study area to assess how such a tool can help achieve the optimal land use layout. Additionally, the outputs of the ACO are compared with the results of two other meta-heuristics (i.e., the Genetic and the Simulated Annealing algorithms) to evaluate the performance of the designed DSS.
Methods: To fulfill the research objective, first, the land use optimization problem is formulated, which includes the decision variable and how it is discretized, three objective functions (i.e., compatibility, compactness, and suitability maximization), two area controlling constraints, and the way of combining the objective functions. Second, the ACO algorithm customized with the land use allocation problem is presented. Third, the study area, the 7th municipal district of Isfahan divided into 334 allocation cells, is introduced, and the requirements such as parameters and weights for calculating and combining the objective functions are described based on the case study characteristics, related studies, and expert opinions. Fourth, a code is developed, and a GUI is designed in MATLAB programming to carry out the computational process, solve the equations, and handle the spatial data. Finally, the ACO parameters are tuned, and the code is applied to the study area within the depicted DSS framework. Alongside the ACO implementation, two other meta-heuristics (i.e., the genetic and simulated annealing algorithms) are executed to constitute a ground for the performance analysis.
Findings: Outputs of the developed DSS illustrated the land use distribution within the 7th municipal district of Isfahan and the ACO’s convergence process. It showed that the cultural and sports land types were in the central part of the study area, and a major amount of the service land types was placed close to the green spaces. In addition, service types were located in the central and northern parts of the study area providing access for the residents to such necessary amenities.
Conclusion: The results indicated that the ACO algorithm performed satisfactorily in the study area. In other words, the DSS, including this algorithm, demonstrated effective land management and planning performance. It also displayed benefits for users interested in applying different objectives and constraints. Besides, the ACO performed better in the study area than the other utilized methods. Although this article delivered a DSS along with optimization algorithms advantageous for resource management and spatial planning, incorporating land use levels (e.g., urban and neighborhood) and compatibility of the modeling context with more realistic conditions (e.g., cell area variation) are proposed for future research that are of limitations of this article.
Keywords
Main Subjects
COPYRIGHTS
© 2024 The Author(s). This is an open-access article distributed under the terms and conditions of the Creative Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/)
)