Urban Planning
Abolfazl Ghanbari; Mir Hossein Pourbagher
Abstract
In this study, using images of Landsat-8, Landsat-7 and Sentinel-2 satellites in the coding environment of Google Earth Engine, their uses and changes during the two periods before and after urbanization (from 2000 to 2008 and from 2008 to 2019) will be categorized and then the next five-year development ...
Read More
In this study, using images of Landsat-8, Landsat-7 and Sentinel-2 satellites in the coding environment of Google Earth Engine, their uses and changes during the two periods before and after urbanization (from 2000 to 2008 and from 2008 to 2019) will be categorized and then the next five-year development forecast of Sahand city (until 2025) will be made. Perceptron multilayer artificial neural network (MLP) method has been used as a method for predicting spatial multi-criteria decision making (MCDM). The independent variables used in the present study in predicting the physical development of the city are land price, type of use, slope, slope direction, altitude, distance from urban areas, distance from waterway network, distance from fault, distance from network Passages (main and secondary). The results of classification of satellite images showed that the physical development of Sahand new city has been done in order to turn barren lands into urban land. In addition, physical development was built to turn cheaper land into areas. The built lands have been greatly developed and from 64,155 square meters in 2000 to 682,192 square meters in 2019. Among the image classification methods for land use extraction, the SVM method was the best method and also the Sentinel-2 satellite images had the highest accuracy. The multilayer perceptron artificial neural network was used to predict the future physical development of the new city of Sahand, which according to studies, the development is predicted in directions that are based on the cheapness of the land and the limitations. Geomorphological is like slope and altitude.
Urban Planning
Hassan Mahmoudzadeh; Mohammad Samadi; Majid paydar
Abstract
The city of Tabriz, which has the fastest urban growth in the northwest of the country, is one of the largest cities in Iran in terms of population, economic activity, industry and transportation options. Public transportation and industry combustion and lack of proper filtration of these industries, ...
Read More
The city of Tabriz, which has the fastest urban growth in the northwest of the country, is one of the largest cities in Iran in terms of population, economic activity, industry and transportation options. Public transportation and industry combustion and lack of proper filtration of these industries, such as thermal power plants, has led to increased air pollution in the city. For this purpose, the present study tries to use input variables (distance from industrial centers, humidity, temperature, population density, distance from commercial centers, distance from bus stations, distance from educational centers, vegetation changes, distance from free Roads, building density, wind direction, carbon dioxide and carbon monoxide) to assess air pollution using artificial neural networks in the metropolis of Tabriz. In the present study, the independent variables affecting the distribution of pollution probability in two models of multilayer perceptron neural network (MLP) and linear regression were tried to be defined by defining measures in urban management and influencing and planning the mentioned variables.Improve pollution control.The results show that the major pollutants are mostly suspended particles (PM10), gas (CO2), (SO2) and (NOx).The dispersion of airborne particles is mostlydue to vehicle traffic, industrial activities, fuel combustion of diesel engines and construction and the need to generate more electricity.-The activities of thermal power plants, Tabriz refinery and domestic and commercial heating systems are also among the factors producing SO2 and the highest CO2 production is related to the fuel of gasoline-burning vehicles.The intensity of the increase in the amount of this pollutant in all selected stations in the autumn and winter seasons is much higher, so that in these seasons the pollutants reach more than twice the allowable level.The share of Tabriz air pollutants can be divided into three general categories, the most important of which is the thermal power plant and transportation.
Climatology
Monir Shirzad; Hajar Feyzi; Majid Rezaei Banafsheh
Abstract
Introduction Reference evaporation and transpiration is one of the important elements of the hydrological cycle, which plays an important role in agricultural studies, water resource management plans, irrigation and drainage network design and water structures (Nuri et al., 2013, Volume twenty, ...
Read More
Introduction Reference evaporation and transpiration is one of the important elements of the hydrological cycle, which plays an important role in agricultural studies, water resource management plans, irrigation and drainage network design and water structures (Nuri et al., 2013, Volume twenty, number five, page 12). Due to the small amount of precipitation and the limitation of water resources in Iran, the correct management of water resources is very important and it is necessary to be careful in using water.Data and MethodIn order to carry out this research, daily climatic data during the years 2014 to 2015 of East Azerbaijan (four stations of Maragheh, Midane, Jolfa and Ahar) were prepared from the regional meteorological organization. After normalization and determination of correlation, the data were used in MATLAB software with artificial neural network method with Lunberg-Marquardt training to 70-30 combination for training and simulation. The input data for the simulation of evaporation and transpiration (temperature, sunshine hours, humidity, wind speed) and the work evaluation criteria are RMSE, R2 and MAE, which we gave priority to the data with less error. Results and DiscussionIn this research, the method based on artificial intelligence (ANN) and three experimental models (Penman Monteith Fau (PMF56), Blaney Kridel (B-C) and Kimberly Penman (K-P) were used to model the non-linear transpiration evaporation system of the reference plant. The results showed that the artificial intelligence method has better accuracy and speed in estimating ET0 compared to experimental methodsConclusionThe results showed that the artificial intelligence method has better accuracy and speed. Also, comparing the method of artificial neural networks with classical methods, the results indicate the appropriateness of the performance of artificial neural networks.
Climatology
Hashem Rostamzadeh; Aliakbar Rasuly; Majid Wazifedoust; nasser maleki
Abstract
Introduction Floods are a natural occurrence that causes casualties, livestock losses and damage to buildings, facilities, gardens, fields and natural resources every year. Therefore, rainfall estimates have long been considered by researchers in various fields, and along with the advancement of science ...
Read More
Introduction Floods are a natural occurrence that causes casualties, livestock losses and damage to buildings, facilities, gardens, fields and natural resources every year. Therefore, rainfall estimates have long been considered by researchers in various fields, and along with the advancement of science and the emergence of new technologies, many advances have been made in the methods of rainfall estimation and evaluation and validation to achieve the best method. In the last twenty years, there has been a lot of progress in rainfall estimation methods. This advancement is due to the possibility of using a lot of information from different parts of the world, better understanding of atmospheric phenomena, exchanges and atmospheric rotations, improving the performance of models, progress in various surveillance tools such as radar and satellite and computer power. The methods used to estimate precipitation, especially in the short term, have shortcomings and are generally based on numerical forecasting models or the use of empirical analyzes, which are usually not very accurate for multi-hour intervals, so the use of satellite data It has been recommended as a supplement to address this problem, and doing so could greatly help increase the accuracy of numerical models for rainfall estimates. Methodology The study used the physical properties of a cloud of five waves between 2011 and 2015. The data of the second generation of MSG meteorological satellite has good coverage on different regions of Iran. The satellite has 12 channels on the region and produces accurate products. Some of these products are in line with the physical properties of the cloud used in this study. These products are produced daily every 15 minutes and include cloud peak pressure (CTP), cloud peak temperature (CTT), cloud light depth (COT), thermodynamic cloud phase (CPH), and the volume of water in the cloud. Density (CWP) are the effective radius of cloud droplets (REFF) and cloud type (CT). Was obtained. The criterion for the accuracy of the calculations was the two MAE statistics Equation 1: Equation 2: Results and discussion In this study, TRMM satellite data was considered as control data. After receiving TRMM images in MATLAB software environment, programming was performed and precipitation data were extracted from NETCDF files. After extracting TRMM satellite data, Meteosat satellite products were prepared through the CMSAF database and their data were extracted using MATLAB software code. In the study of waves, the coefficient of determination in the GPR model was 0.72 in the experimental section and 0.77 in the training section. In the TD model, the determination coefficient is calculated in the experimental section 0.64 and in the training section 0.87. However, in the neural network model, the coefficient of determination is 0.68 in the experimental section and 0.72 in the training section. The results show a good relationship between the components studied. Investigating the Effects of Cloud Physical Properties: One of the methods for determining the effectiveness of each of the physical properties of the cloud in estimating rainfall is the sensitivity analysis method. After calculating the coefficient of determination and the error coefficient, the sensitivity of each of the physical properties in estimating the precipitation was performed by the method of calculating the sensitivity analysis. Sensitivity analysis was calculated for all waves. Calculations show that the cloud type is most effective, followed by the effective radius of the cloud droplets and then the optical depth of the cloud in the second and third positions, respectively. Among the physical properties studied, the lowest effect is related to the cloud phase. To investigate the relationship between the physical characteristics of the cloud and the amount of precipitation, five waves of pervasive precipitation were selected between 2011 and 2015. Rainfall data from the region's stations were extracted. In order to validate the TRMM data, a comparison was made between the precipitation data of the selected stations and the precipitation of this satellite. Metoost satellite products were used to extract the physical properties of the cloud. After extracting the data, the physical properties of the cloud were matched to the time scale of the data and evaluated using TRMM satellite rain as a control. Conclusion The selection criteria were such that the waves lasted for at least two days and covered the entire area. On the day of the operation, the precipitation information of the meteorological stations of the region was obtained and also the precipitation information of TRMM satellite was extracted. In order to validate the data of TRMM satellite, the information of meteorological stations was compared with TRMM precipitation and obtained the necessary correlation. In order to get a better result, the matching of numbers was done in terms of time scale. In the next step, using the meteosat satellite products, the physical properties of the cloud were obtained for all waves. Data were extracted at all stages for each pixel. Then the data correlation matrix was performed with three models of GPR, TD and MLPBR, the results of which are given in Table One. Due to the use of different models as well as the study of 8 physical properties of the cloud, the results show a high relationship between the components of the study, so that the coefficient of determination in the GPR model for the experimental and training sections was 0.7 and 0.77, respectively. These coefficients for the TD model in the experimental and training sections are 0.64 and 0.87, respectively. In the artificial network model (MLPBR), the coefficients obtained in the experimental and training sections are 0.68 and 0.72, respectively. The numbers obtained indicate a relatively good relationship between the components. Sensitivity analysis was performed. Sensitivity analysis results show that the cloud type feature has the greatest effect on precipitation and then the effective radius of cloud droplets and then cloud light depth are in the second and third positions, respectively. Among the physical properties studied, the lowest effect is related to the cloud phase.
Climatology
Ali Mohammad khorshiddoust; Kaveh Mohammadpour; Seyed Asaad Hosseini
Abstract
Introduction Prediction of hospital admissions related to climatic parameters is discussed matters that in recent decades in result from climate change, urbanization and air pollution has triggered widespread in many societies. Fluctuations in climatic parameters, in turn, can have a significant impact ...
Read More
Introduction Prediction of hospital admissions related to climatic parameters is discussed matters that in recent decades in result from climate change, urbanization and air pollution has triggered widespread in many societies. Fluctuations in climatic parameters, in turn, can have a significant impact on mortality and mortality, and the use of predictive models can be used to identify fluctuations in climatic parameters affecting disease and their prevalence and planning and Compatibility with the environment to be effective. Methodology Using of predictive models can be consider as an effective tool in managing and controlling the diseases, reducing mortality and planning. Recent study used from Artificial Neural Networks and Logistic Regression models as an effective tool in the prediction of nonlinear processes to predict the rate of asthma admissions related to Climatic parameters in Sanandaj/Sine city. Used data during period of 8-years (2001-2008) collected from synoptic station and Toheid and Beasat hospitals in the Sanandaj/Sine city. Then, the climatic parameters and rate of asthma admissions considered as an input and output data of models, respectively. Result and Discussion The results of the output of two nonlinear models of artificial neural network and Logit in examining the effect of climatic parameters on the number of the asthma patients in Sanandaj/Sine showed that the monthly average parameters with high coefficient of determination (R2=0.98) of temperature (average, minimum, maximum) and QFE pressure in the artificial neural network model and The monthly average minimum temperature, QFF pressure and wind speed (in Knot) in the Logit model have had the greatest impact on the rate of asthma admissions in the city. As the wind speed in the Logit model is more effective than other climatic parameters, that it is clear with the logarithmic superiority (-0.977) and the Wald coefficient (85.616). In general, air pressure, temperature and wind speed are the most effective climatic parameters on the number of asthma patients visiting the hospital. Therefore, depending on the accuracy of the models, the above argument means that among the parameters examined, the elements are more important than other parameters in the city. As the climatic elements have a more effective role in the admission patients to the hospital, and their fluctuations will be more significant in patients' fluctuations. The effects of environmental parameters (climate and pollutants) on diseases have previously been investigated as well, so that the results of previous logistic regression have display a increase respiratory disease, vulnerability of children to asthma and an increase in allergies; In the present study, the results of Logit model (69.5%) also indicate that decrease in the average minimum temperature lead to a decrease in the number of the asthma patients, it means that the rate of asthma is more less in temperatures close to zero or higher and vice versa, the admission more higher in the colder temperature (below zero); in the other words, the more balanced the temperature has the lower the rate, and in the colder the ambient temperature has the highest the number of asthma patients. Thus, comparison the present results and previous studies show that admissions change depending on climate, geographic position and the fluctuation of the elements and then the specific geographical location and the different climatic types of a region will play a decisive role in the number of asthma visitors to hospital. Conclusion The results indicated that Artificial Neural Network model predicted the asthma admissions related to monthly minimum, maximum and average temperatures with considerable accuracy, so that the correlation between actual and predicted data is significant with 0.01 coefficient and 0.99 confidence. Also, Input parameters in the Logit method shows that the rate of asthma admissions affected by parameters of average minimum temperature, average pressure QFF and average wind speed (in knot). In other words, the logarithmic ratio of each of cited parameters is significant with β-coefficients (-0.517), (-0.734) and (-0.977), respectively, that throughout of studied parameters is wind element of effective in asthma admissions then others to the hospital. In general, Artificial Neural Network model showed more sufficiency and accuracy than Logit model. As a result, both Logistic Regression and the Artificial Neural Network methods show that climatic parameters have a greater than 50% effect on the number of asthma patients referred to the hospital (the accuracy models: 69.5 and 98, respectively). In the Artificial Neural Network model, the most accurate possible result shows the more effective role of climatic parameters of temperature and air pressure on the asthma patients. Also, filtering the parameters examined at the output of the Logistic model showed the most possible coefficients for minimum temperature, QFF air pressure and wind speed (knot), among which wind speed was the most important element. Finally, the accuracy of the models showed that the Artificial Neural Network model has a higher accuracy depending on the coefficient of determination and highest correlation. Thus, Artificial Neural Network and Logit as nonlinear methods could well predict the relationship between climatic parameters and the number of the asthma patients. Also, according to the appropriate selection of input parameters and determination of different structures in the neural network is possible to design different models with the highest efficiency and can be considered as an effective and powerful tool in estimating similar studies. Introduction Prediction of hospital admissions related to climatic parameters is discussed matters that in recent decades in result from climate change, urbanization and air pollution has triggered widespread in many societies. Fluctuations in climatic parameters, in turn, can have a significant impact on mortality and mortality, and the use of predictive models can be used to identify fluctuations in climatic parameters affecting disease and their prevalence and planning and Compatibility with the environment to be effective. Methodology Using of predictive models can be consider as an effective tool in managing and controlling the diseases, reducing mortality and planning. Recent study used from Artificial Neural Networks and Logistic Regression modelsasan effective toolinthe prediction ofnonlinearprocessesto predict the rate of asthma admissions related to Climatic parameters in Sanandaj/Sine city. Used data during period of 8-years (2001-2008) collected from synoptic station and Toheid and Beasat hospitals in the Sanandaj/Sine city. Then, the climatic parameters and rate of asthma admissions considered as an input and output data of models, respectively. Result and Discussion The results of the output of two nonlinear models of artificial neural network and Logit in examining the effect of climatic parameters on the number of the asthma patients in Sanandaj/Sine showed that the monthly average parameters with high coefficient of determination (R2=0.98) of temperature (average, minimum, maximum) and QFE pressure in the artificial neural network model and The monthly average minimum temperature, QFF pressure and wind speed (in Knot) in the Logit model have had the greatest impact on the rate of asthma admissions in the city. As the wind speed in the Logit model is more effective than other climatic parameters, that it is clear with the logarithmic superiority (-0.977) and the Wald coefficient (85.616). In general, air pressure, temperature and wind speed are the most effective climatic parameters on the number of asthma patients visiting the hospital. Therefore, depending on the accuracy of the models, the above argument means that among the parameters examined, the elements are more important than other parameters in the city. As the climatic elements have a more effective role in the admission patients to the hospital, and their fluctuations will be more significant in patients' fluctuations. The effects of environmental parameters (climate and pollutants) on diseases have previously been investigated as well, so that the results of previous logistic regression have display a increase respiratory disease, vulnerability of children to asthma and an increase in allergies; In the present study, the results of Logit model (69.5%) also indicate that decrease in the average minimum temperature lead to a decrease in the number of the asthma patients, it means that the rate of asthma is more less in temperatures close to zero or higher and vice versa, the admission more higher in the colder temperature (below zero); in the other words, the more balanced the temperature has the lower the rate, and in the colder the ambient temperature has the highest the number of asthma patients. Thus, comparison the present results and previous studies show that admissions change depending on climate, geographic position and the fluctuationof the elements and then the specific geographical location and the different climatic types of a region will play a decisive role in the number of asthma visitors to hospital. Conclusion The results indicated that Artificial Neural Network model predicted the asthma admissions related to monthly minimum, maximum and average temperatures with considerable accuracy, so that the correlation between actual and predicted data is significant with 0.01coefficient and0.99 confidence.Also, Input parameters in the Logit method shows that the rate of asthma admissions affected by parameters of average minimum temperature, average pressure QFF and average wind speed (in knot). In other words, the logarithmicratio ofeach of citedparametersissignificant with β-coefficients (-0.517), (-0.734)and(-0.977), respectively, thatthroughoutofstudied parametersis windelement of effective in asthma admissionsthen others to thehospital. In general, ArtificialNeural Networkmodelshowed more sufficiencyandaccuracy than Logitmodel. As a result, both Logistic Regression and the Artificial Neural Network methods show that climatic parameters have a greater than 50% effect on the number of asthma patients referred to the hospital (the accuracy models: 69.5 and 98, respectively). In the Artificial Neural Network model, the most accurate possible result shows the more effective role of climatic parameters of temperature and air pressure on the asthma patients. Also, filtering the parameters examined at the output of the Logistic model showed the most possible coefficients for minimum temperature, QFF air pressure and wind speed (knot), among which wind speed was the most important element. Finally, the accuracy of the models showed that the Artificial Neural Network model has a higher accuracy depending on the coefficient of determination and highest correlation. Thus, Artificial Neural Network and Logit as nonlinear methods could well predict the relationship between climatic parameters and the number of the asthma patients. Also, according to the appropriate selection of input parameters and determination of different structures in the neural network is possible to design different models with the highest efficiency and can be considered as an effective and powerful tool in estimating similar studies.
Geotourism
Mohhamadhosen Rezaei moghadam; Mohamadreza Nikjou; Kamran KHalilvalizadeh; Belvasi Imanali; Mehdi Belvasi
Abstract
Landslide is one of the natural hazards in mountainous regions that results in huge losses every year. Alashtar Doab watershed with mountainous terrains, uplands and different natural conditions has the potential for landslide. The purpose of this study is landslide hazard zoning using artificial neural ...
Read More
Landslide is one of the natural hazards in mountainous regions that results in huge losses every year. Alashtar Doab watershed with mountainous terrains, uplands and different natural conditions has the potential for landslide. The purpose of this study is landslide hazard zoning using artificial neural network model in Alashtar Doab watershed. In order to preparing the map, first of all parameters of the landslide were extracted and then the layers were prepared and after that a landslide distribution map that was occurred in the basin was prepared and then by combining landslide influencing factors with landslide distribution map, the impact of each of these factors such as slope, aspect, lithology, rainfall, land use, distance from fault and stream in ArcGIS software were measured. In this research, artificial neural network model with error back propagation algorithm and sigmoid activation function was used. The final structure of the network consisted of eight neurons in the input layer, eleven neurons in the hidden layer and one neuron in the output layer. Network accuracy in the testing phase was calculated by 85.93 percentages. After optimization of the network structure, all area information was imported to the network. Based on landslide hazard zoning using artificial neural network model, 37.44, 45.7, 93.8, 49.32 and 76.6 percent of the area at risk is located in very low, low, medium, high and very high classes, respectively.
Ali Reza Ildoromi; Hamid Zareabyaneh; Maryam Bayatvarkeshy
Volume 17, Issue 43 , October 2013, , Pages 21-40
Abstract
Rainfall due to its noise and random nature has structural changes at different times. Because of large uncertainty, fluctuations in the amount of rainfall forecast is created the prediction of which has been difficult. In this article, precipitation predictability was carried out rescaled by range analysis ...
Read More
Rainfall due to its noise and random nature has structural changes at different times. Because of large uncertainty, fluctuations in the amount of rainfall forecast is created the prediction of which has been difficult. In this article, precipitation predictability was carried out rescaled by range analysis (R/S) technique in Shiraz, Mashhad and Kerman regions. SnapshotHurst (H) showed that rainfall parameter has the ability of predictability, because H was higher than 0.5 and much closer to the value 1. Minimum Hurst value was 0.8 in Mashhad and maximum Hurst value was 0.92 in Shiraz. In order to predict rainfall we used artificial neural network. Type of input parameters based on Pearson correlation test between data from non-rainfall, were a combination of temperature and humidity data. Number of input parameters, the number of middle layers, and other information related to artificial neural network randomly were selected. As a whole, rainfall estimation was calculated through Peresptron multi-layer neural network for comparing the performance of neural network. Results showed that the use of 3 and 4 meteorological parameters has the best rank estimator. Proposed layouts for the Shiraz station is 1-21-21-3, for Kerman 1-25-25-3 and for Mashhad 1-19-19-4 in which 1-25-25-3 of have correlation coefficients more than 91 percent. Validation rainfall models showed that network designed for rainfall parameters has best performance rainfall in Mashhad, Shiraz and Kerman stations with 4, 11 and 14 percent error respectively. As a whole, results showed that neural network method with considering the temperaturel and humidity data for describing the process and their combination in predicting good results were offered.
