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

Abstract

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.

Modelling spatial changes in coastal areas of Samsun (Turkey) using a Cellular Automata-Markov Chain method

“…In the CA-Markov Chain method, the allocation of cells for each LU/LC continues iteratively [15] until the process distributes the estimated quantity of change (transition areas) [2]. The number of iterations is based on the number of time steps (from the base date to the projection date) [11].…”

“…In this study, a 5×5 contiguity filter (Eq. (1)) which has been extensively used to simulate urban expansion [13,15,29,32] was applied to transitionpotential layers. However, the filter can be changed depending on the purpose of the study and analyst's preference/decision [29,33].…”

“…For future projection, LU/LC layer at t2 is accepted as base layer and the transition areas produced by the Markov Chain and the transition-potential layers (suitability layers) for each LU/LC class are used [11,15].…”

“…The transition-potential layers specify the degree to which each cell is suitable for each of the LU/LC types [15]. In the CA-Markov Chain scheme, the process of spatially projecting the LU/LC continues iteratively until the total area determined by the Markov Chain is obtained [11].…”

“…Although numerous studies to determine existing LU/LC and temporal changes in the LU/LC in Samsun have been conducted [16][17][18][19][20][21][22][23], few studies have been published regarding the urban LU/LC changes [15]. In this study, considering the LU/LC for the years 1987 and 2004, an urban expansion simulation for the year 2034 was obtained for the 30-year period starting in 2004, and the trends, magnitudes and spatial distributions of the changes were determined.…”