Introduction
 Population growth and migration of (from or to) cities has led to the construction of unstructured and large changes in the spatial structure and expansion of cities. This causes changes in the surface of the earth and the conversion of natural effects of the earth such as soil and vegetation to the urban texture. So, the first consequence of the expansion of cities is land use change. Today, land use change and land cover have become a major challenge in many countries. Hence, the study of these changes plays a major role in the world's environmental studies. In order to better manage natural and human ecosystems and develop long-term planning, it is necessary to model land use changes and predict future changes.
Methodology
The research method is applied in terms of purpose and  the nature and method of descriptive-analytic research, and the method of data collection in this study is also a library research. In this study, for land use changes during the 29-year period, images were first provided  from the website of the Geological Survey of the United States. Then, using ENVI software, the pre-processing operation was performed to apply atmospheric and radiometric corrections. Also, the specimens of educational and supervised classification of images for land use in four levels (lands, rice field, forests, gardens and Water zone) were studied. Then, in the IDRISI SELVA software, simulation was used to predict future changes using the perceptron neural network.
Results and Discussion
Before the main analysis of the data and the extraction of the information, it is necessary to perform the pre-processing operation. Then several time satellite images used in the research after atmospheric and radiometric corrections were used to prepare the land use map and Maximum likelihood algorithm was used to classify the desired classes. The selection of effective variables in predicting urban growth is an important and useful information for the user to understand the desirability of land use change. Therefore, in the present study, distance variables from the road are considered as independent static variables, and distance from the landfill, distance from the land, and the distance from the forest and gardens are considered as independent variables were used. Among the models that are used in the simulation of land use change, neural networks are multilayered perceptron. Therefore, this model was used to simulate land use changes in this study. Finally, according to the Kramer coefficient, the distance from the road has the least effect and the distance variable of the land has the greatest impact on land use change and transmission potential modeling. Then, user-potential mapping maps were generated through multi-layer perceptron neural networks for an 8-year time span. Also, in the maps produced, regions with a warm color spectrum have the greatest potential for change, and are more vulnerable to areas with a cool color spectrum.
Conclusion
Today, land use change and land cover have become a major challenge in many countries. These changes have a direct impact on environmental components such as soil, water and atmosphere. Which This causes changes in the surface of the earth and the conversion of natural effects of the earth such as soil and vegetation to the urban texture. Due to the fact that the city of Lahijan, like many other cities in Iran, has faced expansion of construction in recent years, so, today, the city has undergone significant changes in land use. The purpose of this study is to model and predict land use changes using the Multilayer Perceptron, . In this regard, in order to implement this model, Landsat classified satellite images for the four periods of 1989, 2000, 2010 and 2018, as well as four independent variables including distance from the road, distance from Shalizar, distance from the forest and gardens, And and distance from the land, were built to simulate land use changes. The study resulted in the generation of transmission potential mapping with the 84.58 accuracy index, which shows that the distance from the land constructed  the greatest impact and the distance from the road has the least effect on land use change variations.

 

Extended abstract
Introduction
Land use is one of the most important biophysical and socio-economic characteristics in any watershed. The science of land change has recently been introduced as one of the fundamental components of global environmental change and sustainable development research. Monitoring land changes is important in future planning and natural resource management. Therefore, the need to detect such changes in an ecosystem is very important. Therefore, the need to detect such changes in an ecosystem is very important to take appropriate action if necessary. . Due to the fact that Lake Urmia is an important ecotourism center in Azerbaijan, with the drying up of the lake, Greater Azerbaijan and all the areas affected by this phenomenon will face a recession of domestic tourists. These factors, in turn, will lead to the migration of residents of the villages of this region to the surrounding cities and social problems in these cities. Its catchment area has been one of the water resources of this area[r11] . But the extent to which these changes, and especially the change in land use, have taken place, requires special study. In general, it is possible to study land use changes in both terrestrial and remote sensing methods. However, in recent decades, with the development of hardware and software facilities for processing satellite images, as well as the ease of access to multi-spectral and ultraviolet images, the use of remote sensing techniques to produce land use maps has become more common. The use of remote sensing technology has a special place in natural resource studies. Multi-time comparison, information updates, digital processing, data diversity, and data transfer speeds have made remote sensing the most important technology in detecting changes.
Methodology
The approach of the present study is developmental-applied and its descriptive-analytical method. According to the subject of the research and in line with the objectives defined in this research, satellite image with the specifications listed in Table (1) and the softwares of Google Earth, ENVI4.8, ArcGIS10.2 have been used. To use satellite imagery to perform techniques, all images must have the same coordinates. Remote sensing techniques, especially those used to classify land use and detect changes, are usually monitored and analyzed based on similar pixels in multi-time images; Corrections, images are not properly geometrically and radiometrically corrected, research accuracy is reduced. Thus, the satellite images of 1989, 2000, 2016, and 2019 were returned to the image with an RMS error of 0.42 pixels, capturing 20 control points from the image surface to the image method. In geometric correction, the ground control points were tried to have a good distribution at the image level so that the mathematical model used to calculate the unknown coefficients in the equation would have less error. To convert the corrected image coordinates to the non-corrected image, a second-order function was used. . In this study, the numerical value reduction method of dark pixels for radiometric correction of images has been used. In this method, a constant value of the total value of the pixels in a given band is reduced to apply radiometric corrections to each satellite image. In the next step, the images were mosaic due to the location of the study area in two women (1368-348)[r12] . Then, using field visits and the global location apparatus, instructional samples for each use (lake, agriculture, salt marsh, other lands) were identified in the study area.
Results and discussion
In this study, three supervised classification methods (neural network, backup vector machine and maximum probability) have been used to extract land use maps. By comparing the accuracy of the classification obtained from the methods mentioned in Table (2), it was found that the classification method of the backing vector machine with a cap rate of 99.75% is more accurate than other methods. According to the results of both classification methods of machine vector support and neural network, precise methods for extracting land uses and in separating the phenomena that have close spectral behavior are very successful, especially support vector machine  , which . Which was a bit successful.[r13] 
Conclusion
In this study, first, images of measuring satellites (MSS-TM-OLI) were used and the map of Urmia Lake, lake landscaping and its surroundings were was extracted by applying supervised classification (support vector machine, neural network and maximum probability). . Comparison of image stratification methods showed that the support vector machine method has more classification accuracy than the other two methods due to its general accuracy and higher capability coefficient. The results also show that satellite imagery has a significant ability to extract land uses. Also, in order to investigate the trend of land use change, maps extracted from satellite imagery in 1989, 2000, 2016 and 2019 were compared. Examination of land use maps in the three mentioned periods showed significant changes in land cover. These changes include: Agricultural land use area has increased significantly from 1989 to 2019 due to the favorable area for agriculture and drilling wells. Numerous and the use of aquifers has been underground . Analysis of Landsat satellite images showed that significant fluctuations in the lake's water level have occurred over the years. So so that the water level changes of Urmia Lake from 1989 to 2016 have increased from 5348 to about 2705 square kilometers. However, from 2016 to 2019, due to heavy cross-sectional rains, it had an increase in water area of ​​1644 square kilometers. The images also show that the coastline, especially in the east and southeast of the study area, has a significant number of boys. From 1989 to 2000, the area of ​​this land use increased by 378 square kilometers. Also, between 2000 and 2016, its area continued to rise and increased to 786 square kilometers. However, due to the increase in cross-sectional rainfall during 2016 to 2019, the water level of the lake has increased and some of the salt marshes have been submerged and the land use area of ​​the salt marshes has decreased by 838 square kilometers.