@article{ author = {Miraki, M. and Sohrabi, H. and Fatehi, P. and Kneubuehler, M.}, title = {Comparison of Machine Learning Algorithms for Broad Leaf Species Classification Using UAV-RGB Images}, abstract ={Abstract: Knowing the tree species combination of forests provides valuable information for studying the forest’s economic value, fire risk assessment, biodiversity monitoring, and wildlife habitat improvement. Fieldwork is often time-consuming and labor-required, free satellite data are available in coarse resolution and the use of manned aircraft is relatively costly. Recently, unmanned aerial vehicles (UAV) have been attended to be an easy-to-use, cost-effective tool for the classification of trees. In fact, given the cost-efficient nature of UAV derived SfM, coupled with its ease of application, it became a popular choice. The type of imagery is an important factor in classification analysis because the spatial and spectral resolution can influence the accuracy of classification. On the other hand, classification algorithms also play an important role in the accuracy of tree species identification. So, this study investigated the performance of four classifiers for tree species classification using UAV-based high-resolution imagery in broadleaf forests and takes a comparative approach to examine the three non-parametric classifiers including support vector machines (SVM), random forest (RF), artificial neural network (ANN), and one parametric classifier including linear discriminant analysis (LDA) classifiers in heterogeneous forests of Noor city located in Mazandaran province. In June 2019, the study area was photographed. The field survey was carried out to record the species and position of the mature overstory trees which were clearly identifiable on the orthomosaics. Individual tree crowns were clipped by one-meter buffer and the digit numbers were summarized at for each tree by computing descriptive statistics from the orthomosaics. Using zonal statistics, mean, standard deviation, variance, unique, range, mode, and median were calculated for raw bands (Red, Green, Blue), vegetation indices (NRB, NGB), and band ratios (G/R, R/B) from RGB orthomosaics. We classified the tree into 4 classes: Parrotia persica (Ironwood tree), Populus capsica (Caspian poplar), Ulmus minor (Common Elm), and Quercus castaneifolia (Chestnut-leaved oak). Finally, the classification algorithms were applied using R software. The classification accuracy for identified trees was performed using 10-fold cross-validation by computing the producer’s accuracy, user’s accuracy, and Overall accuracy. All algorithms resulted in overall accuracies above 80%. Of course, the results showed that, as a parametric algorithm, LDA with an overall accuracy of 0.87 provided the best results for tree classification, because it does not require the tuning of free parameters. As for parameter value, the mean was the most important that this can be related to the similarity of this feature in any sample. Caspian poplar with user accuracy of 0.97 and Ironwood tree with user accuracy of 0.72 had the highest and lowest classification accuracy, respectively. Caspian poplar high accuracy is probably due to its crown color which is quite different from the other species. The main error (misclassification) is a classification between “Ironwood tree” and “Common Elm” classes. This may be caused by the fact that the spectral signatures between Ironwood tree and Common Elm trees are very similar. In general, our study showed that UAV derived orthomosaic can be used for tree classification with very high accuracy in mix broadleaf forests by different algorithms.}, Keywords = {Linear Discriminant Analysis, Support Vector Machine, Random Forest, Artificial Neural Network, UAV, Spectral Indices}, volume = {10}, Number = {2}, pages = {1-10}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-926-en.html}, eprint = {http://jgst.issgeac.ir/article-1-926-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Hassanpour, P. and Feizizadeh, B. and ValizadehKamran, Kh.}, title = {Readiness Assessment of Implementation of Enterprise Spatial Data Infrastructure in Agriculture Jahad Organization of West Azarbaijan Province}, abstract ={Spatial data infrastructure (SDI) refers to a basic collection of technologies, policies, and organizational arrangements which creates a platform for sharing location information for users at all levels of the organization up to national and international. patial Data Infrastructure (SDI) is known as a fundamental comprehensive approach of spatial data managing and sharing. Due to the complexity of establishing SDI, creating SDI has been considered as serious challenge, especially in developing countries. Successful and sustainable SDI can be developed when social, organizational and cultural issues are resolved in harmony with the technological ones. The main goal of SDI implementation is to overcome the problem of duplication of data collection by organizations, which leads to wasting financial funds and time. SDIs have been developed for use at global, regional, national, state and local levels.  Technically, SDIs involve a very intricate digital environment, such as a wide range of geospatial databases, networks, standards, metadata, institutional structures and technologies.  The framework of the present research is constructed on the basis of a survey and an SDI readiness model. Following a review of the research background, and taking into account the interaction of relevant indicators, criteria for establishing SDI were identified. This research aims to apply readiness assessment of SDI implementation in enterprise SDI approach. To achieve this goal, the agricultural-Jahad organization was elected as case of enterprise SDI. In this context, within the first step the affecting factors for the successful SDI-implementation were identified and requested data were collected in the form of a questionnaire during the specialized interviews with experts, mangers and decision makers. In this regard, the statues of organization related to spatial data availability, motivation, skill, perception, policy, financial resources, organizational structure, technology, human resources and information status were assessed. Accordingly, the analytical network process (ANP) was applied to compute the criteria weights and determine the significance of each factor for successful SDI implementation. The criteria weights were obtained and decision model was accordingly organized. The overall results also indicate that there is a low level of awareness of SDI in the organization and also one of the major challenges for the organization is the lack of specific policies and guidelines for data generation, data storage and sharing. However, one of the key strengths for successful SDI implementation in Jahad organization is the high motivation and telecommunications platforms for data exchange between organizations and appropriate computer systems. Subsequently, the possibility of successful implementation of SDI was evaluated and analyzed using the Likert scale and the results showed that the minimum chance of SDI implementation in pessimistic mode was 60.7% and in optimistic mode 85.37%. Summary of the results of need assessment and feasibility studies show that it is possible due to SDI deployment conditions in Agriculture Jahad organization of West Azarbaijan province. Due to the large number of stakeholders, data sharing, technology and network requirements, developing SDI is a very cost-effective technology. In every society, but especially in developing countries like Iran, there are also a significant number of threats affecting the development of SDI. SDI-readiness assessment leads to the identification of challenges and issues, and therefore helps to minimize their impacts on successfully developing SDI. Thus, we conclude that the results are of great importance for analyzing the factors which may have significant impact on successful SDI development in Agriculture Jahad organization of West Azerbaijan province.}, Keywords = {Spatial Information Infrastructure (SDI), Readiness assessment, Agricultural Jihad, West Azerbaijan}, volume = {10}, Number = {2}, pages = {11-21}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-914-en.html}, eprint = {http://jgst.issgeac.ir/article-1-914-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Izakian, Z. and Mesgari, M. S.}, title = {A Hybrid Time Series Clustering Method Based on Fuzzy C-Means Algorithm: An Agreement Based Clustering Approach}, abstract ={In recent years, the advancement of information gathering technologies such as GPS and GSM networks have led to huge complex datasets such as time series and trajectories. As a result it is essential to use appropriate methods to analyze the produced large raw datasets. Extracting useful information from large data sets has always been one of the most important challenges in different sciences, and data mining techniques provide useful solutions to solve this problem. Nowadays, clustering technique as the most widely used function of data mining, has attracted the attention of many researchers in various sciences. Due to different applications, the problem of clustering time series data has become highly popular and many approaches have been presented in this field. An efficient clustering method groups data in such a way that the objects in the same cluster are more similar to each other than to objects in different clusters. In order to compute the difference/similarity between time series data in clustering process, a similarity measure or distance function is used. Therefore, choosing an appropriate distance function is one of the most important challenges that should be considered before starting the clustering process. So far, various distance functions have been proposed to measure the difference/similarity between time series and each of them have its own strengths and weaknesses. Since choosing a suitable distance function to cluster a specific data set is a complicated process, in this study, we proposed a clustering method based on combination of the well-known Fuzzy C-Means (FCM) method and the Particle Swarm Optimization with the ability of using different distance functions in time series clustering process. In this way, the step of choosing the best distance function before starting time series clustering procedure has been deleted and different similarity measures can participate in the clustering process with different impacts. The objective function in this study is defined based on Fuzzy C-Means clustering objective function and the particle Swarm Optimization algorithm is used to find the optimal value for the considered objective function. Finally, by considering three distance functions including Euclidean distance, dynamic time warping and Pearson correlation coefficients the proposed method was implemented on seven well-known UCR time series datasets. Also, by considering the average normalized mutual information as a criterion for evaluating the performance of methods in this research, the proposed method was compared with five other methods. The results of this comparison indicated that the method presented in this study performed better in more than 85% of cases rather than other methods. In order to have a better evaluation, Tukey’s multiple comparison tests with a threshold of p < 0.05 is used with the ability of comparing the methods in pairs. The results obtained by Tukey test showed that, in about 83% of cases, the difference between achieved results by the proposed method in this study and results obtained by the other five techniques are statistically significant. Overall, the results of this study clearly showed the superiority of the proposed clustering method in the production of high quality clusters in comparison to some other methods.}, Keywords = {Clustering, Time Series, Particle Swarm Optimization, Fuzzy C-Means}, volume = {10}, Number = {2}, pages = {23-37}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-941-en.html}, eprint = {http://jgst.issgeac.ir/article-1-941-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Kaveh, M. and Yazdi, M. and Dehghani, M. and Sharzei, M.}, title = {Mitigation of Tropospheric Delay on InSAR Interseismic Displacements}, abstract ={One of the major challenges of Interferometric Synthetic Aperture Radar (InSAR) technique is the existence of tropospheric effect on the results. The tropospheric effect is due to the changes of atmospheric parameters including temperature, pressure, and humidity between the master and slave images. In this research, two different methods based on spatial-temporal filters and calculation of phase delay using MERIS data were evaluated. The main objective is to monitor the interseismic deformation across the Tasouj fault located in West and East Azarbaijan provinces. To this end, Stanford Method for Persistent Scatterer (StaMPS) is applied on 12 ascending ENVISAT ASAR images spanning between 2004 and 2008. The deformation time series obtained from StaMPS are two rough due to the atmospheric effect. In the first method employed for the atmospheric effect reduction,  considering that the atmospheric effect is a temporally-decorrelated and spatially-correlated signal, two different high pass and low pass filters are applied in the temporal and spatial space in order to extract the atmospheric signal which is then subtracted from the time series analysis results. In the second method, the phase delay due to the troposphere is estimated using the MERIS water vapor product. GPS measurements are finally used in order to evaluate the performance of different atmospheric reduction methods. Two quantitative criteria, i.e. Root Mean Square Error (RMSE) calculated from GPS and corrected time series and standard deviation of atmospherically-corrected time series are considered as two relevant methods for evaluating the fluctuations reduction. The method based on spatial-temporal filters shows more superiority over the other one with RMSE and standard deviation of 13 mm and 40 mm, respectively, at its best case.  }, Keywords = {Persistent Scatterer, Tropospheric Corrections, GPS, MERIS, Interseismic}, volume = {10}, Number = {2}, pages = {39-56}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-897-en.html}, eprint = {http://jgst.issgeac.ir/article-1-897-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Sadeghi, B. and Samadzadegan, F. and Dadrasjavan, F.}, title = {3D Classification of Urban Features Based on Integration of Structural and Spectral Information from UAV Imagery}, abstract ={Three-dimensional classification of urban features is one of the important tools for urban management and the basis of many analyzes in photogrammetry and remote sensing. Therefore, it is applied in many applications such as planning, urban management and disaster management. In this study, dense point clouds extracted from dense image matching is applied for classification in urban areas. Applied images are acquired using a Micasense RedEdge multispectral camera to increase the classification accuracy. The band to band registration is one of the existing challenges of multi-spectral camera, which the SIFT algorithm is used to extract the corresponding features of each band. One band selected as reference and other bands are transferred to the reference band by projective transformation. Finally, the bands are combined to create a color image from each three bands. So, two point clouds are generated using dense image matching techniques from two sets of images. To produce a multi-spectral point cloud, the two set of point clouds have been integrated using nearest neighbor interpolation. The multi-spectral point clouds are classified by using random forest algorithm, structural and multi-spectral features. This process composed of three parts as structural information, multi-spectral information, and integration of both. Finally, the results are shown a 25% improvement in the accuracy of the integration of multi-spectral and structural information compared to multi-spectral information and 32% improvement in the accuracy of the integration of multi-spectral and structural information compared to structural information. Classification using visible information (RGB) instead of multispectral information resulted in an accuracy drop by 5%.}, Keywords = {3D Classification, Dense Image Matching, Multispectral Image, Band to Band Registration, Point Cloud, Random Forest}, volume = {10}, Number = {2}, pages = {57-78}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-898-en.html}, eprint = {http://jgst.issgeac.ir/article-1-898-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Ahangarha, M. and SaadatSeresht, M. and Shahhoseini, R. and Seyyedi, S. T.}, title = {Crop Land Change Monitoring Based on Deep Learning Algorithm Using Multi-temporal Hyperspectral Images}, abstract ={Change detection is done with the purpose of analyzing two or more images of a region that has been obtained at different times which is Generally one of the most important applications of satellite imagery is urban development, environmental inspection, agricultural monitoring, hazard assessment, and natural disaster. The purpose of using deep learning algorithms, in particular, convolutional neural networks and hyperspectral imagery, here is to identify the planting area because these networks have an excellent performance in achieving change detection. In this research, we investigate to use of deep learning methods in comparison with another tradition methods for obtaining changes in an agricultural area so that, after generating difference images with the use of Otsu algorithm we generate a preliminary binary map. Then we extracted the feature by using sparse auto encoder networks and classified pixels in two categories to change and no change by using the convolutional neural networks too. In the end, we obtain a final change map by making a model and evaluation of accuracy. That we have achieved even better results, which indicates the need to use deep learning methods. Since solving, the problem manually related to change detection. To investigate capable of the proposed method, 2 datasets hyperspectral imagery from the American Hermiston agricultural fields in the United States was used and vegetation cover near the Shadegan wetland located in the south of Khuzestan province, evaluated by the Hyperion sensor. The proposed method compared to other methods has an overall accuracy of 95% and the kappa coefficient of 0.86.}, Keywords = {Change Detection, Deep Learning, Hyperspectral Images, Sparse Auto Encoder, Agriculture Monitoring}, volume = {10}, Number = {2}, pages = {79-89}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-860-en.html}, eprint = {http://jgst.issgeac.ir/article-1-860-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Shariyari, H. and Emami, H.}, title = {Forest Fire Potential Modeling and Simulation of its Extension Using Remote Sensing Data and GIS: (A Protected Area of Arasbaran)}, abstract ={Forest fire models are generally used in different aspects of fire management and are helpful in understanding and prediction of fire behavior. Forest fires cause a significant damage for public property by destroying a large tract of forest.  This helps fire fighters to focus on an area with greater risk and to develop better substructure for fire fighter training and ultimately to plan fire-fighting policies to minimize damage and stay safe. In the same way simulation modeling also provides an adequate tool to estimate risk when actual risk data are limited or unavailable. Ultimately there is a need to model forest fire in ground, crown, and surface fuel. Forest fire risk assessment, which based on an integrated index, becomes an important tool for forest fires management. The integrated index includes the information about fuel, topography and weather condition which constitute potential fire environment together. The fuel and weather condition are essential for forest fire occurrence, so the main potential fire environment parameters in the process of the forest fire risk assessment are temperature, fuel moisture content and vegetation status. The environment parameters data for traditional forest fire risk assessment were always obtained from the weather station. In present study forest fire risk was estimated as the proportion of simulation runs that burned a particular point and was accumulated over the entire study area. Study used satellite remote sensing datasets in conjunction with topographic, vegetation and climate datasets to infer the causative factors of fires. Spatial data on all these parameters have been aggregated and organized in a GIS (Geographic Information System) framework.  In this research, the relation between the most effective environmental elements (vegetation index (VI), Land surface temperature (LST), slope, aspect, wind speed and direction) and human factors (vicinity of roads and residential areas) has been investigated as a mathematical model with the occurrence and release of fire in the forest protected area of Arasbaran. In order to validate the results, the data from previous fire burns has been used.To this end, LDCM satellite imagery, digital elevation model, wind speed and direction, and other parameters were used in synthesis remote sensing and geographic information systems. At first, a combination of environmental factors, fire hazard maps and map of areas with a 50% fire risk was produced. Then to simulate its extension, Alexandria's semi-experimental models and cellular automation algorithms were used and the genetic algorithm is used to optimize the model parameters. The obtained results of normalized correlation coefficients of environmental parameters showed that VI, LST, slope and aspect were 29.20%, 29.11%, 21.93% and 19.75%, have the greatest correlation with the risk of fire map, respectively. In addition, about 17% of the study area have a high fire risk potential and more than 50% of the area is in a high fire hazard. In addition to environmental elements, the study of the relation between human factors and fire risk showed that the proximity to the road had the highest share in the incidence of fire. Also, the simulation results of synthesis of the Alexandros semi-experimental and cellular automation models showed that expansion of fire in the first region of the test have an overall accuracy 95.56% and kappa 91.41% and an overall accuracy 62.69% and Kappa of 13.13% compared to the reference data in the second region of the test. These results were in good agreement with the results of the simulation studies in firefighting development. Therefore, the simulation process can be used to protect the forest effectively. Results from the current study were quite significant in identifying potential active-spots of fire risk, where forest fire protection measures can be taken in advance.}, Keywords = {Forest Fire, Simulation of Fire Spread, Arasbaran Region, Remote Sensing}, volume = {10}, Number = {2}, pages = {91-109}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-817-en.html}, eprint = {http://jgst.issgeac.ir/article-1-817-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Ghadimi, M. and Derakhshan, A.}, title = {Behaviour Comparison of the Taleqan Dam Using Instrumentation Data and Radar Interferometry}, abstract ={Dams are one of the most important fundamental structures all around the world. Given the high volume of water in the dams, they are susceptible to damage and destruction, leading to large financial losses and fatality. Therefore, by installation of instrumentation data in the dam’s body and execution of terrestrial surveying network, stability and safety of dams can be monitored. However, occasionally abnormal processes take place in the dam’s body and foundation that do not match with the instrumentation data’s outcomes. In the recent years, with the evolution and progress of radar imaging techniques and the image processing approaches, large deformations in the dams’ and bridges’ body can be monitored precisely. In the current study, the abnormal deformation and displacement taken place within the time period of Sentinel-1A 2014-2018 on the downstream part of Taleqan dam’s body were evaluated 4 mm/y and were compared with instrumentation data. The results imply that the occurred displacement is related to the external and protective layer of the dam’s body (Riprap) and has no correlation with the dam’s body behaviour.}, Keywords = {InSAR, Behaviour of Taleqan Dam, Sentinel1-A,}, volume = {10}, Number = {2}, pages = {111-117}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-873-en.html}, eprint = {http://jgst.issgeac.ir/article-1-873-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Abbasi, O. R. and Alesheikh, A. A.}, title = {Georeferencing Semi-Structured Place-Based Web Resources Using Machine Learning}, abstract ={In recent years, the shared content on the web has had significant growth. A great part of these information are publicly available in the form of semi-strunctured data. Moreover, a significant amount of these information are related to place. Such types of information refer to a location on the earth, however, they do not contain any explicit coordinates. In this research, we tried to georeference the semi-structured resources on the web using machine learning. To this end, we leveraged the advertisements related to real state domain in the city of Tehran, Iran, published in Divar website. In order to extract the advertisesments from the website, a crawling approach was chosen. In addition, to assign coordinates to advertisements, we used Random Forests algorithm. The results show that using this approach, the advertisements can be georeferenced at the precision of neighborhoods. The resulting presicion from this approach is about 2 km and 6 km in latitude and longitude directions, respectively. Moreover, the results demonstrate that price of the property has higher importance relative to other variables considered in this study. It can be concluded that the price of properties in Tehran shows stronger spatial pattern in North-South direction than East-West direction.  }, Keywords = {Georeferencing, Place-Based Data, Random Forests, Web Resources}, volume = {10}, Number = {2}, pages = {119-129}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-927-en.html}, eprint = {http://jgst.issgeac.ir/article-1-927-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Heydarivaraste, S. and Emadi, S. R. and Jamour, Y.}, title = {Estimation and Analysis of Precipitable Water Vapor Using GPS Data and Satellite Altimeter}, abstract ={Determination of water vapor in the atmosphere plays an important role in forecasting weather conditions and precipitation studies. For this reason, it is very important to study the tropospheric delay, especially the wet component, which is due to the presence of water vapor in the atmosphere. In this paper, the amount of water vapor was estimated by altimeter satellite radiometer and GPS data, which were based on GPS results and compared with satellite altimeter results. For this purpose, observations of 16 and 133 transmissions of Jason-3 satellites with a period of 10 days in 2018 were used. After processing the altimeter satellite observations using BRAT 3.3 software, the average amount of precipitation water vapor in this method for Tonekabon, Urmia and Bandar Abbas cities was 45, 44 and 30 mm, respectively. In the GPS method, using the Precise point positioning algorithm (PPP), the total tropospheric delay in the vertical direction was obtained (ZTD) and then the hydrostatic delay (ZHD) was subtracted from the total delay and finally by applying the relevant conversion factor to Non-hydrostatic delay (ZWD), the amount of precipitating water vapor was estimated.With processing GPS observations of three permanent stations of Tonekabon, Urmia and Bandar Abbas in 2018 corresponding to the observations of 16 and 133 transmissions of Jason-3 satellite with a time interval of 10 days and using From Bernese 5.2 software, the average amount of precipitable water vapor was estimated to be 47, 45 and 31 mm, respectively. Finally, the amount of RMS and standard deviation from the two methods were estimated to be 1 to 1.5 mm and 5 to 5.5 mm, respectively. The closeness of the results obtained from the two methods shows a very high agreement and compatibility between these two methods with a correlation coefficient of about 0.98 and the ability to combine them for climate and weather studies.}, Keywords = {Precipitable Water Vapor, Troposphere , GPS , Satellite Altimetry, Jason Satellite}, volume = {10}, Number = {2}, pages = {131-139}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-942-en.html}, eprint = {http://jgst.issgeac.ir/article-1-942-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Hashemi, V. and Mesgari, M. S. and MohammadiKazaj, P.}, title = {Solving the Ride-Sharing Problem with Non-Homogeneous Vehicles by Using an Improved Genetic Algorithm with Innovative Mutation Operators and Local Search Methods}, abstract ={An increase in the number of vehicles in cities leads to several problems, including air pollution, noise pollution, and congestion. To overcome these problems, we need to use new urban management methods, such as using intelligent transportation systems like ride-sharing systems. The purpose of this study is to create and implement an improved genetic algorithms model for ride-sharing with non-homogeneous vehicles (like taxis and vans with a capacity of 4 and 10 passengers). The proposed genetic algorithm can group passengers according to their trip similarity based on Spatio-temporal parameters to reduce the number of empty seats in vehicles, followed by the number of vehicles through the city, and get the optimal traveling path for each group of passengers. Optimal traveling path planning should also be considered to minimize each group's travel distance and, as a result, the time delays during the trip for each passenger and driver. Therefore, in this algorithm, four objective functions are considered. The objectives include minimizing the total travel distance of trips, the entire time delay (deviation from ideal times) at the origin and destination of passengers, number of vehicles, and number of empty seats. Due to the previous studies and the lack of combination of these objective functions mentioned above, in this article, complete research was conducted to create a model by combining these objective functions. Combining these objective functions complicates the model and, consequently, presents challenges in its implementation. To overcome these problems, Two innovative mutation operators and two local search algorithms under the titles of genetic algorithm and innovative algorithm based on passengers' travel time priority proposed to improve the genetic algorithm's exploitation ability and to reach the global optimum answer. The first innovative mutation operator is called join-vehicles. This innovative operator aimed to reduce the number of used vehicles by using vehicles' maximum capacity to serve passengers. As discussed in this paper, conventional mutation operators such as insert or scramble operators do not have adequate ability to solve this problem. In this innovative method, the indices of two genes related to two random vehicles' positions in the entered chromosome are chosen randomly. The goal is to remove the second vehicle and combine its passengers with the first vehicle to travel beside its passengers. Also, the arrangement of boarding and disembarking this set of passengers is planned in a way that the car's capacity condition is always satisfied; therefore, there will no longer be a restriction on passengers' combination in a van with a taxi vice versa. The second innovative mutation operator was proposed to change the van into a taxi. During the training, we would observe that some vans were used to serve the passengers while less than half of their capacity was occupied. At first, this operator replaces the van vehicles on the input chromosome with random taxis not used on the chromosome and recalculates this chromosome's cost with the new state. If this new state reduces the chromosome's cost, the taxi will be replaced with that van in the chromosome. Another issue that arises after applying the mentioned mutation operators on the chromosome is how to take turns for passengers to board and disembark in altered parts of the chromosome to respond to requests optimally. Therefore, two local search algorithms based on the innovative passengers' time priority to board and disembark and the traditional genetic algorithm have been implemented to increase the solution quality. These two algorithms are applied to the altered part(s) of the input chromosome and replace the resulting output with this/these part(s). About the innovative local search algorithm based on the time priority of boarding and disembarking passengers, a passenger whose expected time to board is earlier than the other passengers of a group gets on the vehicle first. This passenger's expected time to get off at his destination is compared with the other passengers' expected time to board if he/she has higher priority than the others. Then the vehicle reaches him/her to his/her destination first. Then the vehicle goes to the origin of the next passenger, who has more priority to get in the vehicle. According to passengers' expected time priority, this procedure is repeated to board and disembark them properly. In this model, 18 travel requests, including 26 passengers (some travel requests included more than one passenger), were considered, which want to be transferred in a hypothetical road network that contains 46 nodes and 75 edges. Finally, the implemented model was tested and evaluated during six different scenarios. The results indicate the efficiency of the implemented model of this paper. It should be noted that according to the chromosome encoding method used in this paper, which is similar to some previous studies, the model of this paper can be used, tested, and evaluated in other areas related to the vehicle routing problem.}, Keywords = {Ride-Sharing, Improved Genetic Algorithm, Metaheuristic Mutation Operator, Local Search Algorithm}, volume = {10}, Number = {2}, pages = {141-163}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-923-en.html}, eprint = {http://jgst.issgeac.ir/article-1-923-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Nadri, M. and AkhoondzadehHanzaei, M.}, title = {Anomaly Detection in Time Series of Chlorophyll Around the Time and Location of Large Coastal Earthquakes Using Random Forest Method}, abstract ={Earthquake is one of the most devastating natural hazards which efforts to predict the time, location and magnitude of it have not been yet completely successful. Remote Sensing data is proved to be an effective source of information about lithospheric and atmospheric activities around the impending earthquakes which are referred to as earthquake precursors. The issue of detecting anomalies in these precursors has been interesting to many researchers. One of the precursors that has been taken into consideration by the researchers, is the chlorophyll-a (chl-a) concentration on the sea surface. Since, over %70 of the Earth's surface is covered by water and many seismic active faults are located in coastal belts of the continents, the behavior of oceanic earthquake-related parameters such as Sea Surface Temperature (SST), surface latent heat flux, upwelling index and chl-a, is of particular importance. Elastic strain in rocks, formation of micro-cracks, gas release and other chemical or physical activities in the Earth's crust before and during earthquakes has been reported to cause changes in oceanic parameters. Chl-a parameter is obtained through various methods including laboratory methods of spectroscopy, chlorophyll fluorescence measurement or through satellite data using Color Index (CI) and Raily band ratio (OCX) algorithms etc. Changes from time to time in plankton population in ocean surface and chl-which is the indicator of the primary productivity of phytoplankton biomass in the ocean, can be continuously monitored from space by Ocean Color sensors. In this study, MODIS on Aqua and Terra products were used to examine the pattern of variations of chl-a. By examining the chlorophyll time series of five large earthquakes produced by MODIS sensor products on Aqua and Terra platforms and using a random forest algorithm, it was observed that the release of thermal energy and ground gases due to the activity of Tectonic plates or other physical and chemical activities of the earth's crust before, during and after coastal and near-coastal earthquakes can lead to changes in the amount of chlorophyll in the water surface and this parameter can be used and investigated as an earthquake precursor in future research. The results showed that chlorophyll-a levels exceeded the permissible limits 51, 48, 46 and 28 days before the Gujarat earthquake by 85, 45, 15 and 35%, respectively. In the 2004 Sumatra earthquake in the 20 days before and 18 days after the earthquake, the percentage of chlorophyll-a parameter crossing the upper limit was 110 and 190, respectively. In the 2006 Java earthquake, 42 days before, 15 and 16 days after the earthquake, the amount of chlorophyll-a suddenly changed to 136.84, 52.63 and 107.89% of the allowable threshold. In two other studies, this amount is equal to 199.87, 25, 150 and 190% more than allowable limit, respectively, on the 44th and 34th days before, on the day of the earthquake and 13 days after the Chile earthquake, and 321.42, 50 and 160.71% more than allowable limit 7 and 4 days before and 17 days after the earthquake in Mexico.  In addition, the clear superiority of the Random Forest (RF) algorithm in correct detection of anomalies showed that RF algorithm can be introduced as an effective tool in anomaly detection in time series.}, Keywords = {Earthquakes, Chlorophyll-a, Random Forests, MODIS, Anomaly}, volume = {10}, Number = {2}, pages = {165-174}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-848-en.html}, eprint = {http://jgst.issgeac.ir/article-1-848-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {NekouzadeChaharmahali, E. and Asgari, J.}, title = {Accuracy Improvement of Tropospheric Delay Interpolation in RTK Networks}, abstract ={The effect of troposphere on the signals emitted from global navigation satellite system (GNSS) satellites, appears as an extra delay in the measurement of the signal traveling from the satellite to receiver. This delay depends on the temperature, pressure, humidity as well as the transmitter and receiver antennas location. In GNSS positioning, tropospheric delay effects on accuracy of different components of obtained coordinates. In RTK networks the amount of this parameter is determined by solving double difference observation equations between reference stations and then is interpolated for rover receiver. Tropospheric delay consists of a wet part and a dry part. The dry part that forms about 90 percent of total delay, is related to station height. So in the cases that the height of rover station is significantly different from the average height of reference stations, reduction in accuracy of interpolation is expectable. To investigating this issue, in this article we compared interpolation accuracy of double difference tropospheric delay in two networks with different structure. In both of networks, we have a central receiver that is surrounded with four other receivers. We considered the central receiver as rover station and the others as reference stations. The main difference between these networks is about stations height. In the first network that is named Sima, the difference between the height of rover station and average height of reference stations is 122 meters. The amount of this parameter is 1095 meters for the second network that is named Ebry. To comparing the accuracy of tropospheric delay interpolation in these networks, we determined zenith tropospheric delays (ZTD) for all stations by processing GNSS observations using CSRS-PPP (Canadian Spatial Reference System – Precise Point Positioning) online service. Then we selected the nearest reference station to rover as master reference station. In the following we identified the satellites that were visible in 100 epochs for all stations. Between these satellites, one of them with the most elevation angle was selected as reference satellite. ZTD’s were converted to slant tropospheric delay in satellite-receiver direction using global mapping function. Then double differenced tropospheric delays between the reference satellite and the others and between the master reference station and other reference stations, were determined. Finally this parameter was computed for the position of rover station using interpolation with a two parameter linear equation. After computing RMSE (Root Mean Square Error) of interpolated values, we found that the accuracy of interpolation decreased significantly in the second network. Therefore we can conclude that the difference between the height of rover station and the height of reference stations, has a direct effect on accuracy of tropospheric delay interpolation in RTK networks. So in the following of the article, we introduced a new method to eliminate height variations effects on interpolation accuracy of tropospheric delay. After using this method RMSE of interpolation decreases from 32 mm to 9 mm in the first network and in the second network decreases from 228 mm to 14 mm. in other words we have 69.2 and 93.7 percent of accuracy improvement in these networks. Due to these results, we expect a positive effect on positioning accuracy by applying this method in RTK networks.}, Keywords = {Interpolation, Tropospheric Delay, Double Difference Positioning, Network Real Time Kinematic, Precise Point Positioning}, volume = {10}, Number = {2}, pages = {175-188}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-950-en.html}, eprint = {http://jgst.issgeac.ir/article-1-950-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {Heydari, A. and Amerian, Y. and Mahbuby, H.}, title = {Detection and Modeling of Medium-Scale Travelling Ionospheric Disturbances in Iran Region}, abstract ={Ionosphere layer variations are divided into regular and irregular. Regular changes can be considered as daily changes, changes depending on latitude and changes due to solar activity. Travelling Ionospheric Disturbances (TID) is one of the irregular changes of ionosphere which categorized in small, medium and large scales. Medium-scale Travelling Ionospheric Disturbance (MSTID) which are propagated because of Atmospheric Gravity Waves (AGW) is the main obstacle for accurate interpolation of ionospheric correction in a Global Positioning System (GPS) network, so detection and simulation of these perturbations is necessary. The purpose of this paper is discovering MSTID using carrier phase, which in addition to the values of the total electron content recovered from the observations of GPS also confirm the values detected using the carrier phase observations. MSTIDs are waveforms that have parameters such as amplitude, velocity, direction and wavelength that extracting these parameters are goal of simulation of MSTID. Generally, MSTIDs are planar and longitudinal waves, so to calculate their parameters, first a profile of or dSTEC by constant latitude is considered, then by examining displacement of maximum values of these parameters in a period of time, velocity will be determined. To calculate wavelength, wavelet analysis was used. Results of  and TEC observations were almost identical. MSTIDs have movement in southwest-northeast direction by velocity of 100 meters per second and wavelength of 232 kilometers and amplitude of 0.02 TECU. It means that these perturbations cause an error of 4 millimeters in L1 measurement. Since, phase observation’s precision is 1 millimeter, this error value is significant.  However, the carrier phase observations can be measured with an accuracy of one hundredth of a cycle, which by multiplying this value by the wavelengths of the GPS signal will be about 2 mm. Therefore, error that occurs due to MSTID, it is significant and should be considered.}, Keywords = {MSTID, GPS, TEC, Carrier Phase}, volume = {10}, Number = {2}, pages = {189-198}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-946-en.html}, eprint = {http://jgst.issgeac.ir/article-1-946-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} } @article{ author = {HeidariMozaffar, M. and Varshosaz, M. and Saadatseresht, M.}, title = {Occlusion Area as Suitable Guidance for Terrestrial Laser Scanner Localization}, abstract ={Terrestrial Laser Scanner (TLS) technology, have altered quickly data acquisition for map production in surveying. In many cases, it is impossible to complete surveying of the desired area without TLS displacement in one station to another. Occlusion is innate in data acquisition, with this type of device. To solve this problem, TLS devices should be placed in different locations and scanning operation to be performed. Increase the number of scan stations cause data redundancy and on the other hand will be increases the computational and monetary cost of project. Aim of this paper is presents a novel method for selecting a better place and localization of TLS. Thus, the mechanism of data acquisition was considered by TLS. Also parameters affecting the choice of a place and a station were investigated. Point cloud data investigations show that these parameters have a major impact in reducing the time needed to completeness of data collection. Occlusion as one of the most important parameters has been discussed in this paper. Using data from one station with combination of image processing method, the area of hidden parts to be estimated. Due to the size and area of the various occlusion set, determines to be appropriate locations for new data collection station. After evaluating candidate points according to given criteria, conditional on the project, the next point will be selected for acquisition. By continuous using this method, reduce a ground operation volume in this type of projects. Reducing time of land surveying in many field projects is very important. While ensuring the quality of data and decreased project costs is essential.}, Keywords = {Terrestrial Laser Scanner, Occlusion, Localization, Canny Algorithm}, volume = {10}, Number = {2}, pages = {199-207}, publisher = {انجمن علمي مهندسي نقشه برداري و ژئوماتيک ايران}, url = {http://jgst.issgeac.ir/article-1-51-en.html}, eprint = {http://jgst.issgeac.ir/article-1-51-en.pdf}, journal = {Journal of Geomatics Science and Technology}, issn = {2322-102X}, eissn = {}, year = {2020} }