Mohammad Karimi Firozjaei; Amir Sedighi; Najmeh Neisany Samany
Abstract
Introduction Remote sensing data provide valuable information for the agricultural section and natural resources managers. Nowadays, performance management and estimation via using various methods such as classification and mapping have gained great significance. An example of such data is the mapping ...
Read More
Introduction Remote sensing data provide valuable information for the agricultural section and natural resources managers. Nowadays, performance management and estimation via using various methods such as classification and mapping have gained great significance. An example of such data is the mapping of crops cultivation and orchards at national and regional levels, which is one of the key tools in sustainable agricultural planning and management. These studies appear necessary especially in the field of strategic commodities such as rice and citrus which are among the most important food items for the Iranian people. The spatial information on agricultural lands in the field of agricultural planning and management can help the prevention of the spread of pests, management of the environmental stresses, crop performance estimation and vulnerability assessment in crop production. Field surveys and observations for crops mapping in the growing season in different years are very time-consuming, costly, and only suitable for small-scale studies. In contrast, over the past decades, remote sensing has been recognized as a suitable method for crops mapping for large areas in the shortest time and at low cost. Due to the climatic conditions of the areas in North of Iran, green spaces including vegetation and orchards, and rice fields are located near each other. At the time of the maximum growth of rice products, the spectral characteristics of these land covers are very similar. Therefore, the separation of these two land covers using satellite image classification process faces serious challenges. The aim of this study is to investigate the efficiency of the satellite images and the optimization algorithms for separating green spaces and rice fields from each other at the time of maximum growth. The present study differs from others in this field from two aspects; first, the study compares the capabilities of multispectral and hyperspectral satellite images with each other; additionally, it aims at comparing and evaluating the efficiency of the Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA) so as to determine the optimal features for increasing the separation accuracy of green spaces and rice fields. Materials and methodology This research was carried out based on the two objectives of studying the capabilities of the Hyperion and Landsat images and comparing the efficiency of the PSO and GSA to determine optimal features for the separation of green spaces and rice fields. For this purpose, the two Landsat and Hyperion satellite images as well as ground data sets of the case study in North of Iran were employed. In the first step, preprocessing of the Hyperion and Landsat images was performed. In the second step, various features were extracted from the Hyperion and Landsat images using different spectral indices and transformations. In the third step, the Support Vector Machine (SVM) classifier was applied with two strategies, i.e. the usage of spectral bands and the usage of spectral bands as well as indices as the features in the classification process to extract green spaces and rice fields. In the fourth step, PSO and GSA were employed to extract optimal features from the Hyperion image to distinguish between green spaces and rice fields; then, classification was done with the extracted optimal features; and finally, the efficiency of PSO and GSA were compared to determine the optimal features for the separation of green spaces and rice fields using ground data sets. Results and discussion The results indicate that the use of Landsat image is not effective for the separation of rice fields and green spaces. In other words, due to the high spectral similarity of these land covers, a large percentage of pixels related to the two classes are mistakenly classified in another class. However, the accuracy of the producer and user relating to each class has increased by an average of 10 percent with the addition of spectral indices to the classification process. Using Hyperion image is more effective than Landsat image for the separation of rice fields and green spaces. Moreover, the accuracy for the separation of rice fields and green spaces has increased with the simultaneous consideration of the bands and spectral indices in the classification process. It should be noted that one of the key factors in the efficiency evaluation process of the classification methods is the processing time. The results of using optimization algorithms for determining the optimal features indicate that out of the 150 spectral features (including 140 Hyperion image bands and 10 spectral indices and transformations), using PSO and GSA, only 25 and 31 optimal features were selected for the separation of green spaces and rice fields, respectively.The use of optimal features in the classification increases the accuracy for the separation of green spaces and rice fields more, compared to the use of all features in the classification. Additionally, GSA is superior to PSO when used for extracting optimal features for the separation of green spaces and rice fields. Conclusion The results of this research indicate that the separation accuracy of green spaces and rice fields using Landsat image,is less than that of Hyperion image. With the addition of spectral indices to the classification process, the separation accuracy in both Landsat and Hyperion data increases. Moreover, using an optimization algorithm to determine the optimal features in the classification process will increase the separation accuracy of green spaces and rice fields. Given the overall accuracy values, the efficiency of GSA for separating green spaces and rice fields is higher than PSO.
Meysam Argany; Amir Ramezani; Sadegh Elyasi
Abstract
Extended Abstract
Introduction
Remote sensing science is one of the most powerful tools for the mineral explorations and mineral resource estimation. With regard to this science, any type of rocks with structural characteristics and mineral constituents has a special spectral signature, thus, using ...
Read More
Extended Abstract
Introduction
Remote sensing science is one of the most powerful tools for the mineral explorations and mineral resource estimation. With regard to this science, any type of rocks with structural characteristics and mineral constituents has a special spectral signature, thus, using remote sensing techniques, different types of rocks in a particular area can be recognizable based on their reflective characteristics. Remote sensing techniques are considered as one of the standard methods in geological studies due to the identification of spatial patterns of rocks as well as their speed and economic price. Pervious geological studies indicate that the study area mostly contains basalt, limestone and marble, which has resulted in physical and chemical degradation of basalt stones under the influence of some geological events. Some parts containing basalt have lost their qualities due to these degradations. Therefore, the classification and separation of high-quality basalt zones from low-quality zones is the main objective of this paper.
Materials and method
The main objective of this study is to identify high-quality basalt zones in the Dir-o-Morreh mine located 50 kilometers from Tehran city near the lake of Hoz-e-Soltan. Basalt is a dark-colored and fine-grained igneous rock composed mainly of plagioclase and pyroxene minerals. Typically, this type of rock is formed externally or in the presence of air, such as the flow of lava, and these rocks can also take form intrusively like igneous dikes or narrow pillars. The basalt in the Dir-o-morreh mine is of igneous dike basalt type. In this study, the ASTER satellite multi-spectral images were used. These images allow us to have a good spatial and spectral resolution with regard to the objectives. However, reflectance conversion and atmospheric corrections were carried out on these images before using them, in order to enhance the accuracy of the project. Aerosols contained in the atmosphere are liquid or solid particles suspended in the air, which are very important in the evaluation of satellite imagery for remote sensing. After applying pre-processing, Basalt Exploration Index (BEI) was introduced and used to identify the basalt. The BEI index has been extracted using various sources, including the basalt spectral signature provided by the department of applied mathematics and statistics of Johns Hopkins University, ASTER satellite behavior (defined by the space team of NASA and Japan) and the Earth’s data which were collected to validate the results. This index has been able to identify different basalt zones, including major extraction zones and other potentially possible zones. Moreover, this index is able to completely separate the basalt zones from the surrounding areas (mainly limestone, marble and clay rocks). At the next step, convolution and morphology filters have been applied to separate high-quality Basalt zones from the low-quality. The amount of the brightness of an output pixel from the Convolution filters is a function of weighted average of the brightness of its surrounding pixels. Using convolution with the selected kernel in satellite imagery returns a new filtered spatial image. High-pass Standard convolution filter was used in this study, which eliminates low frequencies of an image by retaining the high frequencies. The morphological nuclei used in this study are only the structural elements of this project and should not be confused with convolution kernels. In order to control the obtained results, the classified zones were double-checked on the field.
Results
The results obtained from the field studies and the identified zones are appropriately consistent with each other using the proposed index. Supervised classification was applied to improve the level of assurance and accuracy. Supervised classification is based on the idea that the user can select sample pixels in an image representing certain classes and then use image processing software using these educational samples as the referral for the classification of all other pixels in the image. This classification algorithm can be very effective and accurate and classifies satellite images in pixel-based or object-oriented form. Supervised classification can result in the preparation of two maps in two different classifications, which is has been done by using the Maximum Likelihood Algorithm. MaxVer or Maximum Likelihood is a statistical classification method that takes the weight of average value of the distance between the classes into consideration, using statistical parameters. To achieve sufficient accuracy, this algorithm requires a number of educational samples or pixels (more than 30). The primary classification includes 5 types of rocks or classes: high-quality basalt, low-quality basalt, limestone, marble stone, and clay which are designated on the map. In order to increase accuracy of the proposed method, the second map was prepared with 3 different classes (low-quality basalt, High-quality basalt, and surrounding rocks) in the second stage.
Conclusion
These maps help us in preparing a new BEI which is more accurate and more capable. It was also able to prove its capability in the latest ground operations and determining the most zones with high-quality basalt.
Zahra Bahari Sojahrood; Reza Aghataher; Mohsen Jafari
Abstract
Extended Abstract Introduction Earth roughness represents a fluctuation of the earth’s surface, and it can be called the complexity of the earth (Wilson, 2012). Roughness calculation is of great importance and is the basis for lots of decision-making. There are various solutions for the roughness ...
Read More
Extended Abstract Introduction Earth roughness represents a fluctuation of the earth’s surface, and it can be called the complexity of the earth (Wilson, 2012). Roughness calculation is of great importance and is the basis for lots of decision-making. There are various solutions for the roughness calculation. The first description of roughness was presented by Kupers, in which the roughness surface is assumed to be a set of points (Kupers, 1957). According to this definition, the deviation from the height criterion of the points is considered as the roughness index. The calculation of roughness in vast areas is possible only through satellite interpretation. The images used for this purpose should be of considerable power (Ghafouri, 1394). The main purpose of this paper is to automatically determine the parts of the area using the digital elevation model (DEM), which are desirable for the user in terms of roughness. To achieve this goal, a local decision-making support system is needed. In most of the mentioned methods, roughness is calculated as a variable in a region. But, the purpose of the paper is to calculate the roughness in different parts and to select the optimal area of the user. In previous methods, in order to achieve the goal, the roughness variable had to be calculated in each range and these ranges had to be compared one by one. This process is time-consuming and sometimes the desirable accuracy is not obtained. Therefore, there is a need for a method that reduces the time and increases the accuracy. For other purposes of this paper, we can refer to the calculation of roughness on a surface. In this research, a new method was developed for determining the areas with the user’s desirable quality of roughness using a DEM and based on the fractal method and spatial decision-making support system and a system with robust tools was designed and implemented for estimating the roughness and it was tested by the digital elevation model of Iran. The results indicate that this method is very accurate. Materials & Methods Ground roughness is an important variable used in the sciences of the earth and astronomy. There is no unique definition for it. It can be defined as a variable to express the variability of the Earth’s surface on a certain scale. In this research, to determine the favorable areas of the user in terms of roughness, a number of methods including sigma T, sigma Z, fractal geometry and a developed method of fractal geometry were used to calculate the roughness. Various spatial analyses were also used in the system. Finally, the spatial decision-making support system was developed for ranking and selecting the patches. Results & Discussion The system was implemented in the ‘Visual Studio’ environment using the ‘C #’ language and the ‘arcengine’ library. This system consists of several parts. First part, is the determination of the area whose roughness is to be determined. The second part, is the extraction of the patches of that area, the third part, which is done after the extraction of spatial complications and descriptive information of each patch, is similar to a filter which is based on roughness calculation methods. The four parts is, the ranking of these patches, and the fifth part, is their classification. The system is designed in such a way that the digital elevation model of any areas with any accuracy can be used. In this research, a 90 meter digital elevation model of Iran and the raster layer of its slope (produced in ArcGIS environment) were used. To display, Google maps were used. This method has a high precision due to its pixel-to-pixel scanning capability of the area and it seems to be more accurate than the existing ones. In most roughness determination methods, there is a method that calculates the roughness in the determined area. But, in this paper, using a spatial decision-making system and using the division of the region into smaller regions, the desired qualitative areas of the user are determined in terms of roughness, therefore, this method is able to decide automatically with regard to the user’s needs. Quality is different for various applications in terms of roughness. Sometimes high roughness and sometimes low roughness is favorable. However, other methods only calculate an amount of roughness of a region and we have to extract the values for each part of the earth and apply the analysis to it, and then compare them to determine their desirability. Several methods of calculating the roughness can also be used in the system simultaneously. Conclusion Earth roughness is a term used to describe the irregularities of an area. In most cases, determining the roughness of the earth is very complicated. There are many methods for calculating the roughness. The proposed method in this project is an innovative idea which is based on spatial analysis, spatial decision-making support system and roughness calculation methods and is calculated using the Digital Elevation Model. The results show that this method is a powerful tool for calculating roughness. In order to improve and continue this work, the correlation of variables is suggested in the calculation and evaluation of the obtained results. In this paper, the values are also calculated at the surface of each patch and in rows regardless of the direction. Various models can be used to consider the order of cells in each patch and compare the results.
Ali Shojaeeian; Sadegh Mokhtari Chelche; Leila Keshtkar; Esmaeil Soleymani rad
Abstract
Nowadays, remote sensing data is able to provide the latest information for the study of land cover and land uses. These images are of high importancedue to the presentation of timely information, diversity of forms, being digital and the possibility of processing in the preparation of user maps.Determining ...
Read More
Nowadays, remote sensing data is able to provide the latest information for the study of land cover and land uses. These images are of high importancedue to the presentation of timely information, diversity of forms, being digital and the possibility of processing in the preparation of user maps.Determining the land cover will be of great help to the area managers to make decisions. In this regard, the purpose of this researchis to compare the efficiency of parametric (least distant and box) and nonparametric (supporting vector machine) methods in land cover classification by using Landsat 8 satellite images in part of Dezful city. The nature of this research has been developmental-practical and its method has been descriptive-analytical. For this purpose, satellite data including Landsat 8 satellite images (13/8/2013) were prepared and analyzed using ENVI software. The efficiency of each classification method was investigated by calculating the two general accuracy and kappa coefficient. The results of the comparison of the methods used in the research showed that the SVM algorithm, especially the three linear, radial and polynomial kernels, had a better and more desirable accuracy than the parametric methods with 97.15%, 95.89% and 95.63% respectively. This study confirms the efficiency and more desirable capability of SVM algorithms in the classification of remote sensing images compared with parametric methods.
Azadeh Zaeri Amirani; Alireza Sofyanian
Volume 21, Issue 83 , November 2012, , Pages 65-69
Abstract
Accessing correct and timely information about urban land use and coverage is especially important for urban planning and management, achieving sustainable development in urban areas and optimal application of land.Impenetrable surfaces are a part of urban coverage with an effective role in changing ...
Read More
Accessing correct and timely information about urban land use and coverage is especially important for urban planning and management, achieving sustainable development in urban areas and optimal application of land.Impenetrable surfaces are a part of urban coverage with an effective role in changing landform and the quality of urban environment. Regarding the importance of such surfaces, different methods of mapping impenetrable surfaces and investigating its changes with satellite imagery exist. These methods can be classified into five general groups: subpixel classification, neural network, classification with VIS model, regression tree model, and spectral composition analysis. Generally, each of these methods have their own advantages and disadvantages, but they are mostly used to detect and classify impenetrable surfaces. The present article investigate impenetrable surfaces and their importance, along with different methods of mapping these surfaces.
Mehran Maghsudi; Sepideh Zandieh
Volume 16, Issue 61 , May 2007, , Pages 35-38
Abstract
Today, almost all reports, scholarly research and applied projects that somehow deal with the dispersion of geographic phenomena use thematic maps. In the European countries production of thematic maps go back to the 17th century, but in our country, the preparation of these maps began with the compilation ...
Read More
Today, almost all reports, scholarly research and applied projects that somehow deal with the dispersion of geographic phenomena use thematic maps. In the European countries production of thematic maps go back to the 17th century, but in our country, the preparation of these maps began with the compilation of atlases by some organizations in the 1960s. A special type of thematic maps which has been widely used, is the choropleth map. Choropleth maps are used to display the distribution of quantitative phenomena over a political or administrative area such as province, city, district and rural districts. Choropleth maps are usually represented by graduated color or hachures. An important point in the development of choropleth maps is to find the appropriate classification system for the data utilized. In fact, there are various classification systems in this regard that may be confused by users if a proper classification system is not selected for information display. In this research, we tried to study the classification methods in choropleth maps and specify the characteristics of each of them.