Urban Growth Simulation of Atakum (Samsun, Turkey) Using Cellular Automata-Markov Chain and Multi-Layer Perceptron-Markov Chain Models

Derya Ozturk

doi:10.3390/rs70505918

Abstract

In this study, urban growth of the Atakum District in Samsun, Turkey, was simulated by Cellular Automata-Markov Chain (CA-MC) and Multi-layer Perceptron-Markov Chain (MLP-MC) hybrid models in a geographical information system (GIS) environment. Historical land use/land cover (LU/LC) data were extracted from 1989, 2000 and 2013 Landsat TM/ETM+/OLI images. Using the LU/LC data for the years 1989 and 2000, the urban growth for 2013 was simulated using the CA-MC and MLP-MC models. The simulation results were compared with the 2013 LU/LC data to assess the validity of the simulation. The MLP-MC method provided the best results according to the validation based on the kappa index of agreement. Based on this result, the urban growth for the year 2025 was simulated using MLP-MC. The simulation estimated an urban growth rate of 35.2% between 2013 and 2025, an increase in the area of artificial surfaces from 1681.9 ha to 2274.3 ha and the destruction of 511.7 ha of agricultural land and 4.4 ha of forest. The results of this study demonstrate that the urban growth models provide a better understanding of the current patterns and temporal dynamics and can predict future changes according to past and current dynamics. The results also show that simulations are most accurate when using a model that best conforms to the changes in the given study area.

Highlights

The urbanization process causes cities to rapidly grow and spread out over wide areas
To better understand the land use/land cover (LU/LC) changes and urban growth dynamics, the results were divided into four parts: i. composition of the LU/LC layers for the years 1989, 2000 and 2013 and an accuracy assessment; ii. change analysis of the periods 1989–2000 and 2000–2013; iii. simulation for the year 2013 by the Cellular Automata-Markov Chain (CA-Markov chain (MC)) and Multi-layer Perceptron-Markov Chain (MLP-MC) methods, comparison of the simulation results with the LU/LC data for 2013, and identification of the method that provides the highest accuracy in the study area; and iv. simulation of urban growth for the year 2025 using the method that produced the best results in the 2013 simulation
This study focused on the accurate determination of the future urban growth potential of Atakum and the natural areas that are at risk due to urbanization

Summary

Introduction

The urbanization process causes cities to rapidly grow and spread out over wide areas. Urban analysis is defined as the solution to urban problems through revealing the current conditions of a city [15,16]; the method requires interdisciplinary research. Issues such as city ecology, socio-economics, demography, urban heat-island effects, assessment of land use/land cover (LU/LC), and the simulation of urban growth can all be addressed within the scope of urban analysis [16,17]. Simulation models are essential in the prediction of future urban changes and in planning studies [18,19]

Objectives

Results

Discussion

Conclusion