Iranian Journal of Remote Sensing & GIS
Year:2019 | Volume:11 | Issue:1|Papers Count:6

In the absence of satellite ephemeris data and inner geometry of satellite’ s sensor, utilization of Rational Function Models (RFMs) is one of the best approaches to georeferencing satellite images and extracting spatial information from them. However, since RFMs have high number of coefficients, then usually high number of control points is needed for their estimation. In the other hand, RFM terms are uninterpretable and all of them causes over-parametrization error which count as the most important weakness of the terrain-dependent RFMs. Utilization of optimization algorithms is one of the best approaches to eliminate these weaknesses. Therefore, various optimization algorithms have been used to discover the optimal composition of RFM’ s terms. Since the mechanism of these algorithms is different, the performance and feature characteristics of these algorithms differ in the discovery of the optimal composition train-dependent RFM’ s terms. But the existing differences not comprehensively analyzed. In this paper, in order to comprehensive assessment the abilities of Genetic Optimization Algorithm (GA), Genetic modified Algorithm (GM), and a modified Particle Swarm Optimization (PSO) in terms of accuracy, quickness, number of control points required, and reliability of results, are evaluated. These methods are evaluated using for different datasets including a GeoEye-1, an IKONOS-2, a SPOT-3-1A, and a SPOT-3-1B satellite images. In terms of accuracy achieved, difference between these methods was less than 0. 4 pixel. In terms of speed of evaluation of parameters, GM was 10 to 12 time more quickly in comparison with two other algorithms. In terms of control points required, degree of freedom of modified PSO was 45. 25 percent and 27 percent more than GM and GA respectively, and finally in terms of reliability, the dispersion of RMSE obtained in 10 runs of three algorithms are relatively same. These results indicated that accuracy and reliability of all three methods are almost the same, speed of GM is higher and modified PSO needs less control points to optimize terrain-dependent RFM.

Nowadays, water supply is one of the main causes of tension for scientists in arid countries. Therefore, the assessment of water resources can be considered as a main challenge for the authorities around the world. Successful dicision making in water resources management tries to resolve competing and conflicting needs of water users from different sectors including: domestic, agriculture and industry. In this research, a systematic framework for assessing different scenarios in the system, has been defined based on WEAP. The proposed model was used in the Urmia Lake basin as a case study; A scenario, proposed by the Urmia Lake Reconstruction Team, presists on transmission of water to the lake. In this study, this scenario and some others, proposed by the Urmia Lake Reconstruction Team, were used in this model and the best scenario was identified using a decision support tool based on the principles of TOPSIS, which has been written in FORTRAN. In the following section, water allocation in the catchment was investigated based on the principles of game theory and the outcome of this research shows that applying game theory and using full cooperation games (based on the Shapley Values method), provides better outcomes for all competing users of water. In other words, using the notion of coalition between different sectors including domestic, agriculture and industry, can save about 332 MCM of water which can be used in the dying lake.

Object detection is one of the fundamental issues in image interpretation process, especially from remote-sensing imagery. One of the most effective and efficient methods in this field is the use of deep learning algorithm for feature extraction and interpretation. An object is a collection of unique patterns that differ with own adjacent properties. This difference usually occurs in one or more features simultaneously, which can be indicated by the difference in shape, color, and gray values. In this regard, the use of deep learning as an efficient branch of machine learning can be useful in generating high-level concepts through learning in different layers. In this research, a database based on the environmental and geographical conditions from some Iranian airports was created. Additionally, an optimal learner model was developed with a convolutional neural network. For this purpose, in the raw data processing section, besides using the transfer learning method, some vectors were extracted to classify the objects and delivered to an SVM model. The output values were compared with the values obtained from the test image for each object, and they were analyzed in a repeatable process for structural matching. Precision of 98. 21% and F1-Measure of 99. 1% was achieved, for identification of the target objects.

Physical activity is one of the most important aspects of life that has many environmental, economic, social and health benefits. According to the importance of the public space of cities in the occurrence of these activities, the issue of developing built environments as a framework that can promote physical activities has become of the major issues in urban societies around the world. This research activities. It has been conducted in an analytical-applied manner, in four areas with a buffer of 500 meters selected from the four urban context of Sanandaj city in Kurdistan province. Through a review of the previous researches, the factors influencing the physical activities have been identified and the data related to each of them have been prepared using the layers of street networks and land uses in geographic information system. The obtained data have been placed in quantitative evaluation formulas related to each criterion. The mentioned evaluations have been studied in a combinational manner and in smartraq and pedestrian orientation indexes, as the two common one. Then, through comparison of the results of the mentioned indexes, the studied areas were classified in groups from high pedestrian oriented to non-pedestrian oriented. The data of physical activities were gathered from 421 inhabitants by questionnaire. The mean of the data has been calculated in SPSS software by variance tests. At the final stage of the research, the relation between pedestrian orientation qualities regression analysis. The results of this research indicate the importance of the built environment on the level of physical activity and hence the public health of residents.

Urban heat islands is the result of urban Climate and one of the important environmental challenges in the 21st century. The aim of this research is to evaluate the combined effects of biophysical components and Land surface temperature with a special Fractal Net Evolution (FNEA) in order to extract the urban heat islands in Tehran. In the first stage, Landsat 8 satellite TIRS 3 images for August, 2013, 2015, and 2015 were calculated for land surface temperature (LST) and the urban heat islands were extracted by adopting a special Fractal Net Evolution (FNEA) Approach. In order to evaluate the role of biophysical components in the formation of urban thermal islands, BI, MNDWI, NDBI, NDVI, SAVI and UI indices were calculated and evaluated. The results showed that there is a negative linear correlation between vegetation and urban heat islands. Also, a strong positive relationship was found between the impenetrable surfaces with urban heat islands in Tehran metropolis. The UHIs of Tehran metropolis with FNEA approach was classified into five categories: cold UHIs, cold second UHIs, medium UHIs, second-order thermal UHIs and warm UHIs, with an average of 95 km2 hot warm islands and 73 km² of the total urban heat islands Tehran metropolis. The most important identified UHIs are also in the 1-zone 21 due to the intense focus of most factories, industrial workshops and warehouses; 2-Zone 9 due to the location of Mehrabad airport, terminals of passenger transportation and main access passage; 3-Zone 22 and North Zone 19 is located because of the focus of Barren land and 4-Zone 13 (uncovered land around the former Dashan Tape airport) and the southern regions of Tehran (due to the existence of educational and industrial workshops).

Agriculture is the basis for development and identification of crops and orchards is an important parameter in agricultural management helping planners through providing precise crop/orchard mapping. In order to overcome the limitations of fieldwork in crop and orchard mapping, satellite images seem to be appropriate due to providing wide coverage, timely and sequentially repeated image acquisition. In this study, IRS-P6 satellite images were analyzed in the Sharveran Plain lands in Mahabad County for orchard mapping. Various spectral indices were extracted using band ratioing and Principal Components Analysis (PCA) methods. Different supervised classifiers were used for classification of a 7-class (land use) and a 2-class (orchard and non-orchard) scenario. The classified maps were evaluated using the ground truth maps. The best overall accuracy and kappa coefficient were 97. 95% and 0. 95, respectively, using Maximum Liklihood classifier in the 2-class scenario. The results showed that IRS-P6 data are very suitable for identification and monitoring of orchards in terms of cost, time and accuracy.