Scenario-Based Cellular Automata and Artificial Neural Networks in Urban Growth Modeling

Abstract

The speed at which cities are growing and developing today cannot be disregarded. Human activities and natural causes are both contributors to urban growth. The relationship between these factors is complex and the complexity makes it difficult for the human mind alone to understand cities. A model that helps reveal the complexity is needed for urban studies. Main objective of this study is to understand the effects of urban planning strategies on the future of the city by utilizing a Cellular Automata and Artificial Neural Networks based simulation model. Driving factors of urban growth according to development scenarios were used in the simulation process. Six different development scenarios were formulated according to the strategic plan of Izmir. Land use and driving factor data used in simulating scenarios were acquired from EarthExplorer and OpenStreetMap databases and produced in QGIS. Future Land Use Simulation Model (FLUS) based on Cellular Automata (CA) and Artificial Neural Networks (ANN) was used. The results were assessed both by using FRAGSTATS which helped calculate fractal dimensions and visual analysis. Fractal dimension results of each scenario showed that the simulation model respected the overall urban complexity. A closer look at each scenario indicated the diverse local growth possibilities for different scenarios. The results show that urban simulation models when used as decision support tools promise a more inclusive and explicit planning process. © 2023 Elsevier B.V. All rights reserved.