نشریه علوم و فنون نقشه برداری
سال دوازدهم شماره 2 (پیاپی 46، پاییز 1401)

Villages located in Isfahan province are one of the areas prone to the spread of cutaneous leishmaniasis, which is characterized by the occurrence of wounds on the skin. To predict the future prevalence of cutaneous leishmaniasis, Continuous monitoring of the spatial distribution of this disease is essential. Disease modeling was performed using two machine learning algorithms called support vector regression (SVR) and multilayer perceptron neural network (MLP). The performance of these algorithms is evaluated using the RMSE index. Analysis of the results shows that SVR algorithm with RMSE = 0.170 compared to MLP with RMSE = 0.348 has better performance. Environmental factors include temperature, humidity, precipitation, altitude and wind speed as independent variables and Estimation of leishmaniasis density was used as a dependent variable in the modeling process, Of which (70%) were used for model training and the remaining (30%) for model evaluation. The results of spatial analysis index showed that The distribution pattern of cutaneous leishmaniasis in the years 1397 to 1399 was clustered.

Nowadays, satellite radar interferometry method plays an important role in calculating natural and artificial displacements, including displacements caused by floods, earthquakes, landslides, drilling of unauthorized wells, drilling of urban tunnels, etc. Metro tunneling is very important due to the importance of preventing irreparable financial and human losses. In Tehran, especially due to the drilling of subway tunnels and lack of attention to underground aqueduct routes and groundwater aquifers, we are witnessing large-scale land subsidence. The use of Multi-Temporal InSAR in determining the interferometry model is very well understood today and it is possible to use these methods to calculate subsidence with very high accuracy in different areas. Of course, these methods also have their own limitations, such as access to appropriate images in the desired time period, changes in coverage of the desired area over time.   In this paper, using satellite images of the Sentinel-1 low-pass in a period of six months (April to October 2019), the subsidence of the Tehran Metro Line 7 tunnel (between Hafdeh Shahrivar St. and Ghiam Square) using the method Radar interferometry is calculated and then compared with field sedimentation performed using sedimentation and precision mapping pins that have a very high accuracy (in the tenth of a millimeter). The number of images used in this period was 22 images, of which seven images with shorter base line length and higher degree of correlation were selected and the interferometry measurement operation was performed in pairs. In the coregistration operation, first two images are precisely aligned on each other and the phase difference between them is obtained by multiplying the conjunction of the first image in the second image which This obtained phase difference is called the interferometric model and at this stage the flat ground phase is eliminated. After obtaining the interferometric model, Deburst operation is performed to integrate the interferometric model and to reduce the volume of calculations, the desired spatial range is specified on the model And the topography phase is eliminated using the strm 3sec DEM. Then, for better performance and phase unwrapping operations, Goldstein filter and SNAPHU package are used, respectively. SNAPHU implements statistical cost and network-flow algorithms to unwrapp phase. The amount of displacement is then calculated from the unwrapped phase. Finally, using these images, the RMSE values ​​for images with VH and VV polarization compared to field data were 2.19 and 20.79 mm, respectively. We will see that the use of VH-polarized images performs better in determining subsidence in urban areas.

Awareness of the marine area is very important for crisis management in the event of an accident. Oil spills are one of the main threats to the marine and coastal environments and seriously affect the marine ecosystem and cause political and environmental concerns because it seriously affects the fragile marine and coastal ecosystem. The rate of discharge of pollutants and its related effects on the marine environment are important parameters in assessing the quality of seawater. Effective monitoring, early detection and estimation of the size of these spots are the first and most important step for a successful cleanup operation and that is essential for the relevant authorities to react in a timely manner and limit marine pollution and prevent further damage. Synthetic-aperture radar (SAR) sensors are a very good choice for this purpose due to their effective operation capability regardless of weather conditions and ambient lighting conditions and large area land cover. Black spots related to oil spills can be clearly detected by SAR sensors, but their visual distinction is a challenging goal. The study used artificial aperture radar (SAR) images from the Sentinel-1 satellite to detect oil spills that distributed by European Space Agency (ESA) via the Copernicus Open Access Hub. This paper provides a deep learning framework for identifying oil spills based on a very large data set from around the world, and using the structure of U-Net, DeepLabV3 + and Fc-DenseNet convolutional networks, it classifies images into two classes. In this study, by changing the loss function and deleting single-class images, much better results were obtained than previous similar works. The IoU results for the U-Net, DeepLabV3 +, and FC-DenseNet models were 0.547, 0.513, and 0.545, respectively.

Wheat is one of the most important grain crop in the world . This kind of plants getting infected by various natural and human factors. Occurrence of disease in this crop may cause disturbance in the circle of economic and management. Therefore prediction and prevention of this disease is one of the main concerns for managers. The method that can help to predict the conditions suitable for disease outbreak can be highly useful. So to achieve this goal, it is tried to study the environmental parameters that makes this disease occur. Then, based on the obtained parameters and using satellite images, the areas that have the potential of the disease outbreak was detected. The study area in this article is Argentina. MODIS satellite images with a spatial resolution of one kilometer is used. Based on previous researches, the parameters such as air temperature, humidity and greenness are the most important parameters to for occurrence of wheat rust disease. The output of this work is an image with two classes of potential zone for rust outbreak and safe zone. The ranges for air temperature, air humidity and greenness for the occurrence of the disease was introduced. Finally an algorithm for identification of the potential zone was introduced. According to the results obtained in this study, the temperature between 2 and 37 degrees Celsius, humidity more than 19% and the NDVI highre than 0. 3 was suitable for the disease outbreak. The overall accuracy in identification of these zones was 90. 70 percent.

Today, tourism is one of the most lucrative industries in the world. Due to the large amount of information that exists about the points of Interest (POI) of a city, the tourist is faced with an overload of information. As a result, a recommending system is needed to recommend suitable tourist places to the tourist in the shortest time. In order to offer a better offer, the interests and context of the tourist should also be considered.In this research, a context-aware recommendation system, based on WEBGIS, has been designed and implemented for the city of Hamedan.In this system, according to the tourist's interests and his context condition, suitable POI are ranked and recommended to the tourist. Tourist interests are examined in ten categories, including recreational attraction, natural attraction, historical and cultural attraction and etc. In addition, in this study, the context of location, time and climatic conditions are considered. To recommend POI, a case-based technique is used that implements a specific style of content-based recommendations. One of the main advantages of this recommending system is the simultaneous attention to the tourist's interests and his tissue condition and offering the shortest path between the recommended places to the tourist. In addition to the suggested tourist attractions, other places including hotels and guesthouses, parking lots and cinemas are also displayed to the tourist in a clustered manner.

In this paper, we propose a quantitative indicator for measuring and ranking real estate from the perspective of the surrounding landscape by integrating the building information model (BIM) and the three-dimensional geospatial information system (3DGIS) based on the AHP method. The landscape is one of the qualitative variables which it's measuring and quantifying is a complex task. In previous studies, mainly, the Hedonic method and 3DGIS-based methods have been used to measure and evaluate the property landscape. The 3DGIS-based methods failed in describing building texture information and the exact position of the observer. Also, modeling and calculating important variables, such as the opinion of local experts, visible surface, vertical and horizontal field of view angles that significantly affect the validity of assessment results is a complex procedure and needs an effective method. For this reason, presenting a new method for scientifically measuring the value of a building's landscape is an attractive research issue. This paper presents a method that combines BIM, 3DGIS and AHP to model, measure and rank real estate with respect to landscape. In the proposed method, the position of the observer, the experts' opinion, the size and position of the windows of the building, field of view angles, diversity, quality and level of landscape are considered. In order to realistically estimate the landscape score, an ordered weighted average (OWA) operator is designed to provide the ability to estimate the landscape score in three modes: optimistic, normal and pessimistic. The performance of the proposed method is evaluated on two apartment units located in two buildings in the area of ​​Chitgar Lake in Tehran. The results of the evaluations indicate the well performance of the proposed formulation.

Many researches have demonstrated that the spatial information can play an important role in the classification of hyperspectral imagery. This study proposes a modified spectral–spatial classification approach for improving the spectral–spatial classification of hyperspectral images. In the proposed method ten spatial/texture features, using mean, standard deviation, contrast, homogeneity, correlation, dissimilarity, energy, entropy, wavelet transform and Gabor filter, are first extracted. The Weighted Genetic algorithm is then used to obtain the subspace of hyperspectral data and texture features. Finally, the hierarchical segmentation and marker-based Minimum Spanning Forest (MSF) classification algorithms are combined with the majority voting law. To evaluate the efficiency of the proposed approach two image datasets, Indiana Pine and Washington DC Mall, were used. Experimental results demonstrate that the proposed approach achieves approximately 10% and 7% better overall accuracy than the Support Vector Machine (SVM) algorithm for these datasets, respectively.

Geographical extent, increasing intensity and the trend of adding new areas are the challenges of researchers and managers in the face of subsidence crisis due to the withdrawal of groundwater resources in Iran. To these challenges must be added secondary crises such as social, security, food and health consequences. In this regard, the importance of continuous and accurate monitoring in the first stage and then zoning of critical areas is the first step in creating a roadmap for land management and control and confrontation of subsidence crisis. In this study, the entire area of ​​Iran enclosed on the Iranian plateau was examined using 132 data frames of Sentinel-1 radar satellites at C-Band wavelength. This study was conducted to discover the amount of vertical surface displacement and its relationship with groundwater abstraction in the period between 2015 and 2017. After measuring the subsidence rate in the plains, in order to zoning the areas, three classes (1) subsidence up to 0.5 cm per month, (2) subsidence from 0.5 to 1 cm per month and (3) subsidence at more than 1 cm per month was introduced. The results showed that an area of ​​28,000 square kilometers of Iranian plains has subsidence. About 7% of these plains, with an area of ​​1,900 square kilometers, suffer at least 12 cm of subsidence annually. On the other hand, about 22% of the plains with an area of ​​about 6,100 square kilometers experience subsidence between 6 and 12 cm per year. However, most of these landslides occurred in an area of ​​20,000 square kilometers, which accounts for 71% of the total area of ​​these plains. The minimum subsidence rate in these areas is 6 cm per year, which is a worrying situation due to its size, amplitude and severity. The results show that 14 provincial capitals and 110 cities are currently either submerged or exposed to it. One of the critical areas is Kashmar plain with a rate of subsidence in the country with a rate of more than 2 cm per month. Akbarabad plains in the south of Shiraz, Rizab plain in the east of Fars province and Shahrmian and Mahdiabad plains in the west of Fars province, Bardsir and Aliabad plains as well as all southern regions of Jiroft including Faryab and Kahnooj plains in Kerman province and Golpayegan plain in Isfahan province were named. In the end, it was suggested that using methods such as (1) continuous field and satellite monitoring (2) accurate measurement of land movement by constructing GNSS stations (3) continuous monitoring in subsidence plains and also (4) dismantling of illegal wells and (5) Monitoring the harvesting of authorized wells, (6) changing the pattern of agriculture and irrigation, and (7) stopping the cultivation of some crops that have high water consumption per capita from the crop calendar, can not exacerbate the current trend of this crisis in the short and long term. . Also, since land subsidence is an irreparable phenomenon even if the groundwater resources increase in the future, it is necessary to draw a roadmap by the Program and Budget Organization and its responsible institutions in the next few decades. The severity of this crisis has diminished.

The limitation of land in big cities has caused the vertical growth of cities; for example, high-rise buildings on the ground and underground urban facilities can be mentioned. This restriction has increased the value of land in cities, and on the other hand, it has created some new and complicated technical and legal aspects in the cadastral issues. To respond to these new technical and legal issues and to better understand and manage the 3D globe, we have to develop a 3D cadastre instead of the existing 2D cadastre. Therefore, it is necessary to use appropriate models and processes considering the new conditions. The use of building information model (BIM) in 3D cadastre has been verified regarding technical and legal support. There are three approaches to providing BIM for existing buildings: 1) using accessible documents and maps, 2) using laser scanners, and 3) using close-range photogrammetry. The main problem in using available documents is the weakness of information on the current status of the building and its internal components. The use of laser scanners is also expensive and is usually non-economical and recommended for large projects. Also, in close-range photogrammetry, the targeting stage is difficult because sticking targets and measuring them takes time and damages interior wall coverage such as plaster, paint, or wallpaper. In this research, using a smartphone and generating a dense cloud of points solved the scale problem before entering the buildings' interior. In addition to increasing the speed and accuracy of BIM preparation, the stage of attaching and measuring targets and damage to the inside of the building was also eliminated. Despite using cheap facilities, the results show that this method reaches an accuracy of 1-2 cm. This accuracy confirms the possibility of using smartphones to map the interior architectural details of buildings and prepare the BIM.

PM 2.5 (particles <2.5 μm in aerodynamic diameter) can be measured by ground station data in urban areas, but the number of these stations and their geographical coverage is limited. Therefore, these data are not adequate for calculating concentrations of Pm2.5 over a large urban area. This study aims to use Aerosol Optical Depth (AOD) satellite images and meteorological data from 2014 to 2017 for spatial distribution simulation of PM 2.5 concentrations over the mega-city of Tehran. The Multilayer Perceptron (MLP), Multiple Linear Regression (MLR), and Decision Tree (DT) models were used to estimate the concentrations of PM 2.5. The results showed that MLP with a root mean square error (RMSE) of 11.46 and R2 coefficient of 0.67 outperformed the MLR and DT models. However, the best model had low prediction accuracy. So, three optimization algorithms, namely, particle swarm optimization (PSO), Genetic Algorithm (GA), and Migration-Based Genetic Algorithm (MBGA) were used to improve the accuracy of the models. The use of GA and MBGA algorithms improved the accuracy of the models significantly and led to the RMSE of 1.71 and R2 of 0.99 for the hybrid model of MBGA-MLP. The proposed hybrid models in this paper can be used to estimate the PM2.5 concentrations.

Drought is one of the consequences of climate change that slowly and over a relatively long period of time affects climate, environment, agriculture, vegetation, water resources and even economic and social sectors. The serious outcome of drought is the reduction of vegetation cover. In this research, using MODIS sensor satellite images of 2001-2020 (20-year period) and CHIRPS monthly rainfall data in Hamedan province, to analyze the effect of drought on phenology parameters (maximum NDVI value, range, base values) NDVI vegetation index has been discussed. For this purpose, the phenology parameters of the NDVI vegetation index were first extracted through the TIMESAT software, next the changes of these parameters were analyzed in relation to the elevation data and the land cover map of the region, and the correlation and RMSE error between the phenology parameters and the elevation data of the region were estimated. Moreover, through CHIRPS raster rainfall data, the annual SPI index was calculated. The results obtained from the analysis of these parameters in different elevations and uses have shown that in 2008, the maximum value of NDVI and the range of NDVI vegetation index have decreased 2008 compared to other years. On the other hand, in 2019, these parameters had higher values compared to other years. In addition, among other phenological parameters, the parameter of base values with a correlation of 0.925 has the highest correlation with the elevation data of the region, and its RMSE is 0.021. Furthermore, through monthly rainfall data for the years 2001 to 2020, it has been shown that in 2008, the average annual rainfall was lower than in other years, and the value of the annual SPI index was -1.79. Therefore, in 2008, a moderate drought occurred in the region, and on the other hand, according to the average rainfall in the years 2007, 2018 to 2020 and the value of the SPI index, during these years, a very severe drought occurred in the region.

The ultimate goal of spatial information, both as part of technology and as science, is to answer questions and issues related to space, place, and location. Therefore, geometry is widely used for description, storage, and analysis. Undoubtedly, one of the most essential features of spatial information is geometric features, and one of the most obvious types of analysis is the geometric type and quantitative measures on such data. Most of the geometric analyzes and measurements used in different sections are based on Euclidean geometry.In other words, most of the known geometric analyzes are based on the assumption that only one line parallel to another line can be drawn from a point outside the line. Therefore, for example, the sum of the internal angles of a triangle should be 180 degrees, and regular tessellation in the plane is possible with only three types of regular polygons. In non-Euclidean geometries, the mentioned assumption and the results of following it are violated and no longer valid. The purpose of this research is to explain the need to use Non-Euclidean geometry. In this research, it is practically shown that location-based social networks or sensor networks can be addressed in the context of non-Euclidean geometry. This research also shows that the geometry governing the location-based social network is a hyperbolic geometry with negative curvature. This fact can be very effective to solve the problems such as routing and clustering. Moreover, the use of Non-Euclidean tessellations is a suitable tool for providing the user's current location service on the map in mobile and ubiquitous GIS.

Iran is a country that has faced all kinds of natural and unnatural accidents throughout history. Due to its vast geographical area, the need to effectively respond to incidents and accidents in the country is considered one of the basic challenges of crisis managers. Planning to minimize the response time is one of the solutions that can be effective in this field due to the preservation of the golden rescue time. In this research, Red Crescent community rescue and relief bases have been evaluated as one of the elements of responding to incidents and accidents that have inherent and legal duties in crisis management, in terms of how to cover based on the optimal response time. In order to achieve the objectives of the research, which is to identify suitable areas for the development of rescue and rescue centers and to determine the functional radius according to the conditions of the region in the axes and the network of different roads and the time of arrival of the rescue centers to the place of danger, from the method of network analysis. and multi-criteria decision making and particle swarm optimization algorithm (PSO) were used. Also, in order to benefit from it as a practical research, all the desired indicators in the instructions for creating a rescue base have been used to optimize the model. The application of spatial restrictions and advantages has been evaluated using the particle swarm optimization algorithm in the main intercity communication network of the country. The results show that the level of roads covered by rescue services has been increased from 33.61% in the current situation to 55.46%.

Due to delay in receiving emergency medical services, a high number of injured people and patients annually lose their lives. Determining the medical service area and correct routing of rescuing operation is influential on the reduction of rescuers’ response time. Changing the traffic flow leads to change of medical service area. Therefore, it is expected that by observing changing traffic, the service area of any hospital would be updated. Using the required hardware and software equipment, which observe traffic flow, would be pricey. In order to utilize such equipment, it is required to have information about the degree of effect of traffic dynamic changes on reducing the service time to the demand points.In this research, the allocation of medical center services using static traffic data was evaluated against the allocation with dynamic traffic data on different days and hours. Then, the influence of different regional areas from traffic changes was investigated. Genetic and particle swarm optimization meta-heuristic algorithms were used in the allocation of services, then the average access time (or response time) to all demand points and border points were investigated separately in the 5th district of Tehran. According to the results, the average response time to all demand points when using static traffic data was 13.4% more than the response time to the same points when using dynamic traffic data. Also, while allocation with static traffic data, the average response time to border points (checkpoints) was 34.2% equivalent to 69 seconds more than allocation with dynamic traffic data. These results reveal an increase in response time delay to border points when services allocation with static traffic data. In addition, in the afternoon hours of the day, which coincide with the increase in requests for assistance, the difference in response time to the demand points during service allocation with static and dynamic traffic data increased. The research results show the important role of dynamic allocation in service improvement.

Proper management of epidemic diseases such as Covid-19 is very important because of its effects on the economy, culture and society of nations. By applying various control strategies such as closing schools, restricting night traffic and mass vaccination program, the spread of this disease has been somewhat controlled but not completely stopped. The main goal of this research is to provide a flexible spatio-temporal model for simulating the spread of the Covid-19 disease in order to investigate and evaluate the effectiveness of vaccination. For this purpose, the combination of Agent Based Modelling (ABM) with changeable input parameters and Geospatial Information System (GIS) has been used. The disease spreads through the interaction of the designed agents with each other and with the environment, with the help of the SEIRD epidemic model, and the characteristics of the agents are monitored during the simulation period. To evaluate the model, the real data of patients with the disease in Urmia city from the time of the outbreak to 140 days later were used. The results show that the implemented model simulates the spread of the disease with MAPE= 32.86% and NRMSE= 8.62%. By simulating the vaccination implementation plan, the total number of infected people will decrease by 36.12% and the total number of deaths will decrease by 44.48%. Comparison of simulation outputs and real data shows a similarity of 82% between model results and reality. The result of this research shows that agent based modelling has been able to simulate the spread of the corona virus to an acceptable extent and evaluate the control strategies effectively; Therefore, agent based models can be used to simulate the spread of different variants of the Corona virus and other epidemic diseases, as well as to simulate the environment's response and control strategies.