@article { author = {Rostami, Rahimeh and Baqeri, Milad and Argany, Meysam and Hasanvand, Mostafa}, title = {Application of ANN Models for Evaluation of Potential and Optimum Pattern of Urban Expansion of Tabriz City}, journal = {Human Geography Research}, volume = {51}, number = {3}, pages = {731-745}, year = {2019}, publisher = {University of Tehran}, issn = {2008-6296}, eissn = {2423-7736}, doi = {10.22059/jhgr.2019.275737.1007860}, abstract = {Introduction An important phenomena in the recent centuries in 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 results in widespread social and environmental impacts including decline in natural spaces, increased vehicle accumulation, reduction in agricultural land with high production potential and decline in water quality. Urban development in any country is not coincidental and on the other hand, controlling its future development 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 and the increased trend of land use change is followed by the loss of valuable ecological land in urban and peri-urban areas due to marginalization, industrial pollution and other human activities. This makes it necessary to performurban development modeling. Tabriz, as one of the most important metropolises of Iran, is physically expanding over time. One of the challenging problems in the development of the city is the lack of proper management 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 in the subject. Methodology There are several methods to determine the appropriate areas for urban growth and one of the effective methods used in this study to select the suitable areas for development in the city is the neural network method. In this study, to determine the optimal location for urban growth, we have used three groups of criteria including socio-economic, land use and biophysical factors in 7 information layers. 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 are including satellite imagery and topographic maps. It is essential to identify the variables affecting the creation of the main prerequisites for the development of land use. In this study, independent variables are including socioeconomic, biophysical and land use. Since there are several decision making rules for exploiting these variables,  the distance between these variables was considered as an indicator. To work with the artificial neural network we have to initially find the effective parameters in urban development as input to the network (INPOT). 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 option. It determines the input layers to deal with new areas. After determining the number of hidden layers in the network structure, the entire study area is provided to train network. The network performed by training points in the province to zoning of the areas with the potential of urban development. Results and discussion MLP network with 16 input layers (effective factors in urban development), 7 intermediate layers (test and error method), and a neuron in the output layer lead to an outline map. Thus, the training was provided to meet new samples. The network was stopped after 15 repetitions and got the necessary training. The network repeats 15 times to find the best possible option with the highest correlation and the lowest error. Conclusion In this study, natural, social and economic factors and urban services such as hospitals, business centers and educational facilities have been included in the model. The results of the research have indicated the vicinity of the city for more suitable development areas.  The industrial areas in the northwest parts of the city are considered due to lack of access to urban services in the fault domain as inappropriate for development in Kandrood village in the southeast of Tabriz. The area has been connected to the city over time and it is is not a good place for urban development because the centers do not have access to services, especially hospitals. On the other hand, this part of Tabriz has gardens and the expansion of residential areas in this part will be accompanied by the destruction of gardens. The areas appropriate for development in the final map are located in the south, southeast and north of the Tabriz city. There are some vacant lots in of the areas of west in some agricultural lands in surrounding areas of the city.}, keywords = {physical development,Tabriz,neural network,Site selection}, title_fa = {ارزیابی پتانسیل و الگوی رشد بهینة شهر تبریز مبتنی بر استفاده از شبکه‌های عصبی}, abstract_fa = {شهر تبریز یکی از کلان‌شهرهای ایران است که گسترش و توسعة روزافزونی دارد. یکی از مشکلات موجود در مسیر توسعة شهرها، مدیریت‌نکردن صحیح آن و بی‌توجهی به عوامل مؤثر است. در سال‌های گذشته، شهر تبریز به دلیل مهاجرپذیر بودن از رشد فیزیکی بسیاری برخوردار بوده است. مدیریت صحیح رشد شهرها از جهات گوناگون از مسائل مهمی است که باید مدنظر قرار بگیرد. روش‌های متعددی برای تعیین مناطق مناسب رشد شهری وجود دارد. یکی از این روش‌ها در تعیین مناطق مناسب برای توسعة شهر روش شبکة عصبی است که در مطالعة حاضر نیز از آن استفاده شده است. در این مطالعه، برای تعیین مکان بهینة رشد شهری از سه گروه معیارهای اجتماعی-اقتصادی، کاربری زمین و بیوفیزیکی استفاده شد. برای مکان‌یابی مناطق مساعد رشد با روش شبکة عصبی، 200 نقطه به‌عنوان نقاط آموزشی شبکه تهیه شدند و لایه‌های میانی نیز هفت عدد بود. نتایج مرتبط با اجزای شبکه نشان می‌دهد با دورشدن از امکانات و مناطق شهری، پتانسیل‌ها به‌شدت کاهش یافته است و بیشتر مناطقی که پتانسیل توسعة شهری دارند، در نزدیک‌ترین فاصلة این امکانات و مناطق شهری قرار دارند. قسمت‌هایی از شهر که طی سال‌های گذشته به‌صورت پراکنده و نامنظم رشد داشته‌اند، با توجه به نتایج حاصل شده نامناسب هستند. همچنین حاشیه‌های نزدیک به هستة اصلی شهر که به خدمات شهری نیز دسترسی بیشتری دارند، برای رشد مناسب‌تر هستند، اما قسمت‌هایی که به‌صورت پراکنده در شمال غرب و جنوب شرق شهر توسعه یافته‌اند کاملاً نامناسب هستند.}, keywords_fa = {physical development,Tabriz,neural network,Site selection}, url = {https://jhgr.ut.ac.ir/article_71556.html}, eprint = {https://jhgr.ut.ac.ir/article_71556_8a0a35fc03ca0763276c3f137680cb99.pdf} }