عنوان مقاله [English]
Tabriz, as one of the metropolises of Iran, is expanding every day. One of the problems that exists in the development of cities is the lack of proper management of it and failure to pay attention to effective factors.In recent years, the city of Tabriz has enjoyed a lot of physical growth due to its immigration status. Correct management of urban growth is one of the key issues that needs to be addressed. There are several methods for determining the appropriate areas for urban growth and one of the effective methods in determining the suitable areas for developing the city is the neural network method, which is used in this study. In this study, to determine the optimal location of urban growth, we use three groups of criteria, Socio-economic, land use and biophysical to locate growth areas with neural network approach 200 points were awarded as training points and 7 layers as intermediate layers were determined. Finally, the results showed with the network components by moving away from facilities and urban areas the potential has fallen sharply and most of the areas with urban development potential are within the nearest distance of these facilities and urban areas. Areas of the city that have grown periodically and regularly over the past years are inappropriate given the results. The results showed that the margins close to the core of the city, which have more access to urban services, are more suitable for growth and sprawling parts in the northwest of the city and south-east of the city are completely inappropriate.
The important phenomena that have occurred in recent centuries in the social and economic life of different countries of the world are the emergence of numerous and new cities, the development of ancient cities, the advancement of urbanization and urban development. Urban development and changes in land use patterns lead to widespread social and environmental impacts. These include reducing natural spaces, increasing vehicle accumulation, reducing agricultural land with high production potential and reducing water quality. Urban development in any country is not coincidental and on the other hand, controlling its future requires careful planning. Understanding the right patterns of urban growth is needed to manage sustainable urban growth and plan for urban development. The high rates of urban population growth in Iran and the lack of urban infrastructure on the one hand, and the increasing trend of land use change, followed by the loss of valuable ecological land in urban and peri-urban areas due to marginalization, pollution industrial and other human activities, on the other hand, provide the necessity of modeling urban development.
The data used in this research can be generally divided into two main categories: the data used to extract land use in the study area, which includes satellite imagery and data that are considered as effective factors on urban expansion and land use change. Identifying the variables that affect the creation of the main prerequisites for the development of land use models. In this study, independent groups of variables including socioeconomic, biophysical and land use were used. Since there are several decision making rules for exploiting these variables, in this study, the distance between these variables was considered as an indicator. To work with the artificial neural network firstly the effective parameters in urban development should be given as input to the network (INPOT), and then a number of educational points are provided to the network, so that the network uses these points (TARGET) to measure the impact of each It determines the input layers, in fact the network has learned the necessary training to deal with new areas. After determining the number of hidden layers in the network structure, the entire study area is provided to the trained network and the network is using what has learned the whole province to zoning with the potential of urban development.
Result and discussion
MLP network with 16 input layers (effective factors in urban development), 7 intermediate layers (test and error method), a neuron in the output layer that leads to an outline map (final map of urban development potential) and the Laufenberg- Marquette was executed And thus, the training was provided to meet new samples. The network stopped after 15 repetitions and got the necessary training. The network repeats 15 to the best possible state, the highest correlation and the lowest error.
In this study, natural, social, economic factors and urban services such as hospitals, business centers and educational facilities are considered. The results of the research have shown the vicinity of the city for more suitable development. And previously scattered areas have been found to be inappropriate. Like the industrial areas of Atlas in the northwest of the city due to lack of access to urban services and placing in the fault domain was inappropriate for development or the Kandrood village in the southeast of Tabriz, which has been connected to the city over time, is not a good place for urban development because the centers do not have access to services, especially hospitals. And on the other hand, this part of Tabriz has garden features and the expansion of residential areas in this part will be accompanied by the destruction of gardens. It seems that the Zanjan-Tabriz highway on the southeast and the presence of gardens, it has led the development of the city over time but the results show if complete planning is done and to focus on all the influential cases, these areas will not be suitable for development. Areas that are appropriate for development in the final map, in the south, south east and north of the city are unused land and only in parts of the West they include some agricultural land that can ignore them to development of the city.
Keywords: physical development, Tabriz, neural network, location