Mohamad Reza Gili; Davoud Ashourloo; Hosein Aghighi; Ali Akbar Matkan; Alireza SHakiba
Introduction:Given that agriculture has the most important role in ensuring food security (Johnston & Kilby,1989), it is necessary to prepare a map that shows the spatial distribution, land area, and type of crops cultivated with high accuracy (Cai et al., 2018). Agricultural land cover is relatively ...
Introduction:Given that agriculture has the most important role in ensuring food security (Johnston & Kilby,1989), it is necessary to prepare a map that shows the spatial distribution, land area, and type of crops cultivated with high accuracy (Cai et al., 2018). Agricultural land cover is relatively dynamic and variable at relatively short intervals. This makes it difficult to classify crops on satellite imagery (Bargiel, 2017). The lack or absence of ground truth data is another cause. Therefore, methods that are less dependent on ground samples and use phenological features derived from time series of bands and vegetation indices to classify crops will be more appropriate (Ashourloo et al., 2020). The purpose of this study is to use a deep learning method based on convolutional networks to classify the crop types and improve the performance of this network by using feature channels as an input image to the network and increasing the classification accuracy. Materials and methods:In this study, the visible and near-infrared bands of Sentinel-2 satellite on 10 different dates from 2019 for an area in Idaho, USA, as an important agricultural area, and the cropland data layer for extracting the crop types ground labels was used (Han et al., 2012). Then, in MATLAB software, the time series of spectral bands were constructed and using them, temporal profiles of NDVI for any crop were extracted to identify the unique phenological features of crops. Then, the functions developed based on the phenological characteristics of crops were applied to the time series of the bands and a feature channel was obtained for each crop that in two separate processes, once bands and once again feature channels were used as input to the CNN and the network was trained and the results of network performance on crop classification in the test site, were compared.Results and discussion:In the first stage, the time series of bands formed the input of the deep convectional neural network and the network was trained in the training area, using the tempo-spectral information of bands as the input channels and crops ground samples as the related labels. Due to the spectral overlap of the crops in some time periods, network training was associated with a relatively high loss and therefore, for the test area, the overall classification accuracy was 69% (percent) and the kappa coefficient was 0.55. In the next step, the functions that were developed as phenological features for crops were applied on the time series of the bands, and for each crop, a feature channel was obtained as the special feature of that crop. Then the algorithm was implemented using these feature channels in the test area and the overall accuracy was upgraded to 86% and the kappa coefficient to 0.82 compared to which indicated a significant improvement in the results compared to the previous case.Conclusion:The deep convolutional neural network is very sensitive to the type of input channels for detecting agricultural crops and selecting the channels with suitable tempo-spectral characteristics for different types of crops, has a great impact on the accuracy of network training and can reduce the loss of training network and increase its efficiency in the classification of various crops.
Omid Ashkriz; Babak Mirbagheri; Ali Akbar Matkan; Alireza Shakiba
Introduction: Urban growth has accelerated in recent decades, therefore, predicting the future growth pattern of the city is very important to prevent environmental, economic, and social problems. The city of Tabriz has also experienced rapid growth of urban lands due to significant demographic changes, ...
Introduction: Urban growth has accelerated in recent decades, therefore, predicting the future growth pattern of the city is very important to prevent environmental, economic, and social problems. The city of Tabriz has also experienced rapid growth of urban lands due to significant demographic changes, which requires accurate simulation of urban growth to prevent negative environmental and economic consequences. The purpose of this study was to evaluate the performance accuracy of the proposed machine learning algorithms by spatial cross-validation method in combination with the cellular automata model to simulate urban growth.Material and methods: In this study, to analyze urban land-use changes, Landsat satellite images related to the years 1997, 2006, and 2015 were classified using the support vector machine algorithm. In the next step, change potential maps of non-urban to urban areas were produced using random forest algorithms, support vector machine, and multilayer perceptron neural network for two periods of calibration (1997 and 2006) and validation (2006 and 2015) based on distance from the main roads, distance from the city center, distance from built-up areas, distance from the rivers and railways, as well as slope, elevation, and two-class (agricultural/barren) land use layer as effective factors in the growth of the city. Finally, using the cellular automata model, the growth simulation of Tabriz city based on land use and change potential maps obtained from machine learning algorithms for the mentioned periods was performed. To prevent over-fitting of algorithms to training samples and to obtain optimistic results, in the process of extracting optimal parameters of machine learning algorithms, the spatial cross-validation method was used to reduce the spatial correlation between training and test data.Results and discussion: The results showed that the random forest algorithm with the area under the ROC curve of 0.9228 compared to the support vector machine and multilayer perceptron neural network algorithms with 0.8951 and 0.8726, respectively, had a better performance in estimating the change potential of non-urban to urban areas. Furthermore, in comparison with others, the random forest also clearly showed local variations in potential change. Finally, the growth of Tabriz city was simulated using the cellular automata model based on the obtained change potential maps. Comparison of the prediction map in the validation period with the current situation of urban areas in 2015 showed that the accuracy of an urban growth simulation model based on random forest with a Figure of Merit index of 0.3569 compared to models based on support vector machine and artificial neural network was more accurate in allocating non-urban to urban lands with 0.3496 and 0.3434, respectively.Conclusion: As machine learning algorithms such as artificial neural networks, support vector machines, and random forest are capable of solving non-linear problems, using them is strongly recommended for urban growth simulation. Also, among the algorithms used in this research, the random forest algorithm based on ensemble learning has a higher advantage than the two-support vector machine and the artificial neural network algorithms.
Amin Hosseiniasl; Mohammad Sadi Mesgari; Ali Akbar Matkan
Volume 16, Issue 2 , July 2018, , Pages 165-184
In water resource allocation, a good division is a major principle which is difficult to determine due to the existence of different criteria. To optimize water resource allocation, it would be efficient to simulate water resource systems in order to consider effective agents and reveal ...
In water resource allocation, a good division is a major principle which is difficult to determine due to the existence of different criteria. To optimize water resource allocation, it would be efficient to simulate water resource systems in order to consider effective agents and reveal the internal interaction among their parts. Various studies show that a multi-agent simulation alone, or in combination with optimization methods, is an effective approach for understanding better the complexities related to water use and users. Also, the genetic algorithm has received attention as an intelligent evolutionary method to optimize non-linear complex problems.
Materials and methods:
The conceptual framework of the proposed water resource allocation presented the interaction between water demand and supply, taking into consideration the economic factors in a sub-basin of Dasht-e Kavir desert in Iran, whose major water source is groundwater. One of the most important duties of water allocators is to achieve optimized allocation of water to different sectors, performed on the basis of the water demands of each consuming agent. Agricultural agents who receive the major portion of water were divided into sub-units. For each product, the diversity of cultivation patterns, deficit irrigation conditions, etc. were considered in order to improve economic status and allocate water resources optimally based on available data and statistics. In industrial uses, products and their functions were discussed as a function governing all businesses. Finally, as water supply is especially important in the drinking sector, the total volume of water required was calculated and completely allocated for this.
Results and discussion:
In the study area, the cultivation of fodder and oil plants is not optimal on the basis of the available water resources with the criterion of maximizing economical profit. Cereals, followed by fruit-bearing trees (including pistachio, pomegranate, grape, and date) have the largest area under cultivation. Results showed that cereals retain their large cultivation area due to deficit irrigation, and the increase in the area under cultivation belonging to garden products is because of their high profitability. Therefore, in the agricultural sector, water allocation can be optimized by using deficit irrigation in cereals and changing the cultivation pattern for products relating to fodder and oil plants. In the industrial sector, the important point is the changing impact of technology on reducing water demand. Since this sector has a higher economical profitability than the agricultural sector, optimized allocation in order to increase economical profitability has led to a water allocation higher than the current consumption level. Evaluation of the optimization results in the genetic algorithm indicates that the convergence rate is high in first iterations and gradually decreases to reach convergence. The convergence of the optimization function is achieved gradually. Moreover, the small variance of changes in the final output of the algorithm (ranging from 0 to 1) suggests the high stability of this algorithm.
Implementation of the proposed framework in the study area increases the economic profitability resulting from optimized water resource allocation to various sectors, if a move is observed from low-efficiency agricultural products to high-efficiency garden products, and the higher allocation of water to industry.
shahram Mohammadi; Ali Akbar Matkan; Seyed Hossain Pourali; Babak Mirbagheri; Parvin Ahmadpour
Volume 15, Issue 2 , July 2017, , Pages 141-162
Introduction: According to distribution requirements and the broad distance between production and consumption centres in Iran, linear infrastructure development plays an important role and should be considered as a vital necessity. Routing problems include many factors which are often incompatible with ...
Introduction: According to distribution requirements and the broad distance between production and consumption centres in Iran, linear infrastructure development plays an important role and should be considered as a vital necessity. Routing problems include many factors which are often incompatible with each other and incompatibility amongst parameters causes significant delays in the process of routing. Hence, it is of interest that use of the new utilities in Geographic Information Systems (GIS) to optimize the routing process can resolve the difficulties faced in decision-making steps. Material and methods: This study aims at optimizing oil pipeline routes from wells drilled to the refinery by using different scenarios and to consider is ORness and ANDness. In the beginning preparation stage all necessary spatial data Like, Geology, land cover, slope, Dem, Fault, Main, River, stream which are required to find the optimal route for establishment of oil transmission line have been collected than Standardization and Preparation by using reducing and Increasing linear weighting function. AHP process has been hired in order to find spatial weight of each parameter’s effectiveness in terms of cost of establishment and oil line interaction with its surrounding environment. Ordered weighted average (OWA) method has been applied to integrate spatial data and achieve the result, cost layer. Dijkstra's algorithm has then been used to find the optimal route between the location of wells and refineries. Results and discussion: The results show that with increase in the value of α, the amount of cost, average slope and height of the oil transit route increase. In scenarios with, higher values are given to high-value pixels. While higher order weights are assigned to values with a lower numerical value in the same position. Therefore, the length of the route from the All (AND) scenario to the At least one (OR) scenario decreases. Because the Dijkstra's algorithm is a single-objective algorithm and aims at extracting the path with the least cost. Because at every move, Choose a pixel with the lowest Accumulative cost as the direction of motion and do not pay attention to the length of the route. Conclusion : By comparing the existing route and the paths obtained from the Dijkstra's algorithm in different scenarios based on the factors of length, cost, mean slope and height of the route extracted In Almost All, Most, and Half (WLC) scenarios, are better than the other options in terms of techno-economic and environmental conditions in study area. Other scenarios have produced better results than some of the existing ones in some of the factors. Providing Various Results, With ORness and tradeoff this method has great flexibility in estimating the needs and priority of decision makers in the field of petroleum industry to design optimal transmission lines.
hassan lashkari; aliakbar matkan; majid azadi; zeinab mohammadi
Volume 14, Issue 4 , January 2017, , Pages 59-74
Introduction: Precipitation is one of the most important atmospheric elements in any climate, and the world climate is categorized on the basis of this climatic element. In some climates, precipitation occurs in all seasons while, in others, precipitation only occurs in cold seasons; in yet other climates, ...
Introduction: Precipitation is one of the most important atmospheric elements in any climate, and the world climate is categorized on the basis of this climatic element. In some climates, precipitation occurs in all seasons while, in others, precipitation only occurs in cold seasons; in yet other climates, it occurs during warm seasons. In most regions that are adjacent to sub-tropical high pressure systems, precipitation occurs only at specific periods of the year. All regions that are located to the North of this system have precipitation during cold seasons although, in practice, the beginning and end of precipitation is not fixed. Sometimes, periods of precipitation occur and, in some years, end much later or sooner than normal. Therefore, in some years, the precipitation period is very short. In the south and southwest of Iran, the period of precipitation and cultivation coincide. Therefore, in this climate region, periods of precipitation are used directly by plants and agriculture products. When the precipitation period is shorter than normal, a part of the plants’ water needs is not provided, and the water resources of the region are influenced intensively by this fact.Materials and Methods: In this research, first, the daily precipitation data of synoptic stations in South and Southwest Iran (including Provinces such as Khuzestan, Kohkilooye-boyerahmad, Lorestan, Busheher, Hormozghan, Chaharmahal va Bakhtiari, Fars and Ilam) over a 36-year period were extracted. In the next step, the start and finish of precipitation periods were determined according to agricultural years in Iran which begin in October. In order to determine the length of the precipitation period in the stations of the south and southwest of Iran the days between start and end of precipitation were calculated. Then, those years in which the precipitation period length was less than 160 days were analyzed as short periods of precipitation. Figure 2 shows the condition of the years investigated in respect of the shortest precipitation period length. Then maps at levels of 700 and 850 HPa were produced for all selected samples from ECMWF data with a resolution of 0.25*0.25 using a scrip in Grads software. The locations of daily cells of sub-tropical high pressure were identified in the selected sample and mapped using ARDGIS10.3 software. The basic component analysis method was used for identifying the pattern of the shortest precipitation period length. Applying basic components analysis to the sea level pressure data led to omission of the patterns with very low repeatability, and patterns having higher repeatability were classified. In this research, the first fifteen components of sea level pressure with 0.934 percent total variance were justified. Finally, the topographic maps and subtropical jet stream for the selected components at levels including 700, 850, 1000, 500, 250 and 300 were analyzed.Results and Discussion: The investigations were conducted on the central cores of the Saudi Arabia high pressure cell in November as the beginning month of precipitation, and March as the end month of precipitation in years with a short precipitation period; these showed that even in November, which was the second precipitation month in the region, the high pressure central core did not have suitable eastward and southward movements. This synoptic pattern caused a situation that even in the second precipitation month, the Saudi Arabian subtropical high pressure system prevents the entrance of Sudanese low pressure, as the most important precipitation system in the region, into the southern and south-western regions of Iran. Meanwhile, the westward movement of high pressure caused a situation where the Mediterranean trough did not extend to lower latitudes. Therefore, the Mediterranean system cannot enter the region. The location of the central core of Saudi Arabian subtropical high pressure showed that the high pressure central cores had earlier westward movement than in other years while, in March, the high pressure nucleus should be located in the East of Saudi Arabia and on the Arabian Sea and Sea of Oman. This westward movement caused a situation whereby Sudanese and Mediterranean low pressure exited the precipitation route of the region earlier than normal; in other words, the precipitation stopped sooner than usual. In these years, the main controlling system in the region was the Siberian high pressure system. During the short period precipitation years, the southern ridge of the Siberian high pressure system in combination with Saudi Arabian high pressure have had a significant southward extension, so that it is extended to the South of the Saudi Arabian peninsula and sometimes to Ethiopia at the lower levels of the atmosphere. In such situations, the Sudanese low cannot enter South and Southwest Iran through its normal routes. As a result, the Sudanese system moves to the West, and enters the eastern Mediterranean with a northward movement and, passing over Sudan and Egypt, and combines with Mediterranean cyclones. In this situation, precipitation occurs later than usual. Conclusion: Saudi Arabian subtropical high pressure plays a fundamental role in the beginning and ending of precipitation periods in the South and Southwest of Iran. With regard to the yearly movement of this high pressure (westward and northward movement during warm periods of the year, and southward and eastward movements during cold periods of the year), it plays a determining role in the beginning and ending of precipitation in this region. For the entrance of the Sudanese system into the south and southwest of Iran, this high pressure system should have a southward movement in order to leave this region and have an eastward movement to provide the necessary conditions for its entrance into this region. But it is observed that in years when the precipitation period in this region is short, the aforementioned system leaves Iran much later, and it has a low eastward movement.
Azadeh kazemi; Hamid Reza Jafari; Ali Torabian; Ali Akbar Matkan
Volume 12, Issue 2 , July 2014
Remote sensing system, especially hyperspectral remote sensing require fundamental knowledge of spectral reflectance of chlorophyll a (chl a) for recognizing eutrophication of inland waters. The first objective of this study was to prepare and investigate the significant differences between the spectral ...
Remote sensing system, especially hyperspectral remote sensing require fundamental knowledge of spectral reflectance of chlorophyll a (chl a) for recognizing eutrophication of inland waters. The first objective of this study was to prepare and investigate the significant differences between the spectral signature of water samples with different amount of chlorophyll a (chl a) of Anzali wetland in 15 cm depth. This was carried out using a full range spectrometer during the spring 2013. The second objective of this study was to discriminate the spectral signature of water samples with different amount of chlorophyll a (chl a) of Anzali wetland in 30 cm depth. A total of 500 water sample spectral curves of illuminated and shaded samples were acquired of 80 water samples with different amount of chlorophyll between 2.07 and 23.9 mg/l. Following the measurements, chlorophyll and total phosphorus of the samples were extracted in laboratory. One important index related to chlorophyll a of water was calculated and statistically analyzed. We conclude that band ratio model in 15 cm depth of water samples has the most relation with chlorophyll a content in comparison with the other indices. This result has been proved by statistical results obtained by chlorophyll and total phosphorus data in lab.
Ali Akbar Matkan; Mohammad Hajeb; Zeinab Azarakhsh
Volume 12, Issue 1 , April 2014
Ali Akbar Matkan,; Mohammad Yazdi,; Davood Ashoorloo; Narges Sadati
Volume 9, Issue 4 , July 2012
The Siyah Bisheh area is located in the central part of Alborz zone, 40 km to the south of Amol. Rock units exposed in the area consist of sedimentary (carbonates, sandstone, siltstone), volcano-sedimentary (andesite to andesitic tuff, tuff), ignimbrite and basalt. Once erosion and tectonism have rendered ...
The Siyah Bisheh area is located in the central part of Alborz zone, 40 km to the south of Amol. Rock units exposed in the area consist of sedimentary (carbonates, sandstone, siltstone), volcano-sedimentary (andesite to andesitic tuff, tuff), ignimbrite and basalt. Once erosion and tectonism have rendered volcanic structures undetectable, remote sensing provides an invaluable tool for their identification and identifying the relationship between lithology and vegetation has shown that the integrated use of remote sensing techniques and field studies can be a powerful tool for distinguishing and mapping the relationships between rock units, structures and alteration zones associated with mineral deposits along the Seyih Bishe area. The main image analysis techniques involved in this study were principal component analysis (PCA) and false color composite (FCC).
Mohsen Ebrahimi Khusfi; Roshanak Darvishzade; Aliakbar Matkan; Davood Ashourloo
Volume 7, Issue 4 , July 2010
Since soil moisture and vegetation cover are the most important parameters effecting drought, analyses of the vegetation fraction and soil spectral signature, especially in the red and infra red bands, are essential in drought estimation. In this study, the Perpendicular Drought Index (PDI), Modified ...
Since soil moisture and vegetation cover are the most important parameters effecting drought, analyses of the vegetation fraction and soil spectral signature, especially in the red and infra red bands, are essential in drought estimation. In this study, the Perpendicular Drought Index (PDI), Modified Perpendicular Drought Index (MPDI) and Vegetation Supply Water Index (VSWI) have been used for drought assessment in arid regions in Central Iran during a time interval of four years (1999-2002). To do this, ETM+ images of LANDSAT 7 for the years 1999 and 2002 and the rainfall statistics for 23 years have been used. Analysis of vegetation cover using vegetation indices demonstrated that in arid regions, changes in vegetation cover were best mapped using a SAVI2 index. The results of MPDI indicated that drought has increased in the rangelands of the study area because of a decrease in seeding of the rangeland and vegetation fraction. PDI showed that the severity of the drought has decreased due to an increase in rainfall in 2002.
Parviz Zeaian Firouzabadi; Alireza Shakiba; Aliakbar Matkan; Ali Sadeghi
Volume 7, Issue 1 , October 2009
This research is committed to providing methodological guidelines for the simulation of urban land use dynamics using GIS, RS and CA models. Urban-CA modeling experiments have been conducted for a medium-sized city (Shahr-e-Kord) in Iran over a thirty-five year time span. Global transition probabilities ...
This research is committed to providing methodological guidelines for the simulation of urban land use dynamics using GIS, RS and CA models. Urban-CA modeling experiments have been conducted for a medium-sized city (Shahr-e-Kord) in Iran over a thirty-five year time span. Global transition probabilities obtained from the Markov chain model and Unique Conditions Map were derived from WoE. Local transition probabilities were estimated using infrastructural factors by two different probabilistic empirical methods: the WoE approach, based on Bayesian theory; and logistic regression. The final land use transition rules drove an Urban-CA model, built upon basis of stochastic land use allocation algorithms. These Urban-CA models drive a CA model based on eight cell Moore neighborhoods. The simulation outputs were statistically validated according to a new compound method based on a Multiple Resolution Model (MRM). After achieving simulations for the 1999-2002 and 2002-2006 time periods along the whole time series, forecast simulations were carried out up to 2025 (1404) and for various urban planning scenarios. For all simulation periods, the best results were obtained from a combined Markov chain and logistic regression with 0.5 Gama to derive the transition rules. Different simulation outputs for the case study indicate their possible further applicability for generating simulation of growth trends both for Iranian cities and cities world-wide.
Seyed Hossein Pourali; Ali Akbar Matkan; Amin Hosseini-asl
Volume 6, Issue 1 , October 2008
Regarding the importance of water sources in Iran, it is necessary to protect better water bodies such as reservoirs. The most efficient way of conserving water sources is to apply proper management to decrease erosion and sedimentation. The first step of this process is to be aware of sediment yield ...
Regarding the importance of water sources in Iran, it is necessary to protect better water bodies such as reservoirs. The most efficient way of conserving water sources is to apply proper management to decrease erosion and sedimentation. The first step of this process is to be aware of sediment yield and identify erosion hazard areas in upper reach of reservoirs. The present study is the preparation of a map of erosion hazard and sedimentation in Dez watershed (area: 17320 km2) which is to be applied in the rehabilitation project of Dez dam. The inaccessible location and the fact that covers a wide area have made the use of satellite images inevitable. In this study, after examining several erosion and sedimentation modeling methods, the PSIAC - with 9 effective parameters - was selected; it is an empirical model in itself. In order to prepare the first series of data, IRS satellite data, Landsat ETM+, basic maps, the Arial photos, helicopter flights and also field checks were all applied. A calibration model with the data achieved from reservoir studies, and taking account of local characteristics of the area, prepared the opportunity to identify and classify erosive zones with GIS. The results which are presented as maps and erosion statistics, not only identify hazardous erosive areas, but also open a new horizon in the field of watershed management and sediment control by having a special outlook towards executive priorities. Keywords: Erosion, Sedimentation, Remote Sensing, GIS, Dez Dam
Amin Hosseini Asl; Ali Akbar Matkan; Farideh Javid,; Hossein Pourali
Volume 5, Issue 2 , January 2008
Remote-sensing and Geographic Information System (GIS) techniques have been utilized in this study to establish a GIS database for Madarsoo watershed in Golestan Province. Among the major constituents of this database we can refer to are: composite multicolor images from LANDSAT TM (30 m resolution); ...
Remote-sensing and Geographic Information System (GIS) techniques have been utilized in this study to establish a GIS database for Madarsoo watershed in Golestan Province. Among the major constituents of this database we can refer to are: composite multicolor images from LANDSAT TM (30 m resolution); Indian IRS 1C/1D (23.5 and 5.8 m resolution) and Quick Bird (60 cm resolution) satellites and land-use/land-cover maps derived from these images; road networks; soil information; Digital Terrain Model (DTM); slope and aspect information derived from Digital Elevation Model; and meteorological and hydrological data. A 'project office' was established with trained personnel at a provincial centre effectively to use the resultant GIS in planning, monitoring and in applications for flood management, as well as to update it regularly. The approach of geographical data base has the potential to store and manage different data with different formats seamlessly. On the other hand it prevents repeating data, decrease errors, and saves the time and expens. The estaldished data base was applied in mike 11 software to hydrological and hydrolical analysis of flood in the studying areaed
Alireza Shakiba; Aliakbar Matkan
Volume 3, Issue 9 , October 2005
Volume 2, Issue 6 , January 2005