ABSTRACT
Housing dispersal in emerging cities should be investigated as it occurs to achieve a better understanding of future housing dispersal. In this study, housing preferences are analyzed in Doha Metropolitan Area based on Gordon’s theory. Machine learning (especially the generalized adversarial network) is utilized to predict the future urban growth of the city. The housing dispersal of expatriates is visualized in the predicted urban growth map of Doha city based on an investigation of housing supply trends, household income levels, government vision, and census data. The study proves the feasibility of this approach for managing urban growth in emerging cities worldwide. It is a robust solution to the increasing imbalance in the urban morphology of metropolitan cities. The conclusions drawn from the broad-spectrum housing dispersal findings of this study will inform policymakers and planners regarding the realities of spatial patterns and future urban growth.
Disclosure Statement
No potential conflict of interest was reported by the authors.
Additional information
Funding
Notes on contributors
Hatem Ibrahim
H. Ibrahim is an associate professor in the Department of Architecture and Urban Planning, Qatar University. His research interests cover urban planning, housing studies, and land-use dynamics in emerging cities.
Ziad Khattab
Z. Khattab is a computer science student at Carnegie Mellon University, and is interested in robotics, machine learning, and computer vision.
Tamer Khattab
T. Khattab is a professor in the Department of Electrical Engineering, Qatar University. His research interests cover information theoretic aspects of communication systems, and optical communication.
Revina Abraham
R. Abraham is a teaching assistant in the Department of Architecture and Urban Planning, Qatar University. She was practicing as an architect and urban planner at Diwan Architects and Qatar Design Consortium.