Residential development simulation based on learning by agent-based model

Authors

DOI:

https://doi.org/10.6093/1970-9870/8980

Keywords:

Agent-Based Model (ABM), Agent Learning, Residential Development, Qazvin

Abstract

Increasing population and desire for urbanization increase housing demand in urban areas and ultimately induce growth and development of residential land-uses that result in urban sprawl. This paper simulates these sprawls of residential land-use in Qazvin city based on learning method by agent-based model. For this purpose, a model with the ability to learn from agents has been developed, in which families as agents can interact with each other and learn based on previous decisions. The model makes it possible to simulate residential land-use conversion based on the agent-based structure over the ten years by applying both demographic changes and household relocation desirability. The multiplication of the average level of land occupation by each family and the number of inserted new families indicates the potential magnitude of land-use changes. Also, results show the priority of residential development locations partially in the northeast regions and a small part of the south of Qazvin. These developments are expected to move towards the east in ten years.

Downloads

Download data is not yet available.

Author Biographies

Hamid Mirzahossein, Department of Civil-Transportation Planning Imam Khomeini International University, Qazvin

Associate Professor in the Civil - Transportation Planning Department of Imam Khomeini International University since 2017. He holds his Ph.D. in transportation planning and engineering from the Iran University of Science and Technology and passed his research scholar at the University of Arizona. He conducts research in transportation and land-use interaction, accessibility modeling, intelligent transportation, and smart city.

Vahid Noferesti, Department of Civil-Transportation Planning, Imam Khomeini International University, Qazvin

Ph.D. candidate in the Civil - Transportation Planning Department at Imam Khomeini International University. He received his master of science from the Iran University of Science and Technology. His interest is machine learning and modeling the land use and transportation interaction.

Xia Jin, Florida International University, Miami, Florida

Dr. Jin is an Associate Professor at Florida International University - College of Engineering & Computing. She holds her Ph.D. in Civil Engineering at the University of Wisconsin – Milwaukee. She conducts research in Activity-Travel Behavior Analysis, Transportation System Modeling and Simulation, Freight planning and modeling, Data Analytics, Land Use-Transportation Interactions, Smart City Initiatives, Geographic Information Systems, Travel Survey Methods, and Emerging Technologies and Mobility Options.

Downloads

Published

31-08-2022

How to Cite

Mirzahossein, H., Noferesti, V., & Jin, X. (2022). Residential development simulation based on learning by agent-based model. TeMA - Journal of Land Use, Mobility and Environment, 15(2), 193–207. https://doi.org/10.6093/1970-9870/8980

Issue

Vol. 15 No. 2 (2022): The city challenges and external agents. Methods, tools and best practices

Section

Focus

License

Authors who publish in this journal agree to the following:

1. Authors retain the rights to their work and give in to the journal the right of first publication of the work simultaneously licensed under a Creative Commons License - Attribution that allows others to share the work indicating the authorship and the initial publication in this journal.

 

2. Authors can adhere to other agreements of non-exclusive license for the distribution of the published version of the work (ex. To deposit it in an institutional repository or to publish it in a monography), provided to indicate that the document was first published in this journal.


3. Authors can distribute their work online (ex. In institutional repositories or in their website) prior to and during the submission process, as it can lead to productive exchanges and it can increase the quotations of the published work (See The Effect of Open Access)