Artificial intelligence for sustainable development of smart cities and urban land-use management

• Published in: Geo-spatial information science Vol. 27; no. 4; pp. 1212 - 1236
• Main Authors: Masoumi, Zohreh, van Genderen, John
• Format: Journal Article
• Language: English
• Published: Wuhan Taylor & Francis 03.07.2024; Taylor & Francis Ltd; Department of Earth Sciences,Institute for Advanced Studies in Basic Sciences(IASBS),Zanjan,Iran; Center for Research in Climate Change and Global Warming(CRCC),Institute for Advanced Studies in Basic Sciences(IASBS),Zanjan,Iran%Department of Earth Observation Science,Faculty of Geoinformation Science and Earth Observation(ITC),University of Twente,Enschede,The Netherlands; Taylor & Francis Group
• Subjects: Algorithms; Artificial intelligence; Cities; Constraints; geo-spatial information sciences; Land management; Land use; Land use management; multi-objective optimization algorithm; Optimization; Performance evaluation; Polynomials; Smart cities; Solution space; Sustainable development; Urban areas; Urban environments; Urban land-use management; smart cities; Urban land-use management; multi-objective optimization algorithm; geo-spatial information sciences; artificial intelligence
• ISSN: 1009-5020; 1993-5153
• DOI: 10.1080/10095020.2023.2184729

The urban land-use allocation problem is a spatial optimization problem that allocates optimum land-uses to specific land units in urban areas. This problem is an NP (nondeterministic polynomial time)-hard problem because of involving many objective functions, many constraints, and complex search space. Moreover, this subject is an important issue in smart cities and newly developed areas of cities to achieve a sustainable arrangement of land-uses. Different types ofMulti-Objective Optimization Algorithms (MOOAs) based on Artificial Intelligence (AI) have been frequently employed, but their ability and performance have not been evaluated and compared properly. This paper aims to employ and compare three commonly used MOOAs i.e. NSGA-II, MOPSO, and MOEA/D in urban land-use allocation problems. Selected algorithms belong to different categories of MOOAs family to investigate their advantage and disadvantages. The objective functions of this study are compatibility, dependency, suitability, and compactness of land-uses and the constraint is compensating of Per-Capita demand in the urban environment. Evaluation of results is based on the dispersion of the solutions, diversity of the solutions' space, and comparing the number of dominant solutions in Pareto-Fronts. The results showed that all three algorithms improved the objective functions related to the current arrangement of the land-uses. However, the run time of NSGA-II is the worst, related to the Diversity Metric (DM) which represents the regularity of the distance between solutions at the highest degree. Moreover, MOPSO provides the best Scattering Diversity Metric (SDM) which shows the diversity of solutions in the solution space. Furthermore, In terms of algorithm execution time, MOEA/D performed better than the other two. So, Decision-makers should consider different aspects in choosing the appropriate MOOA for land-use management problems.