Saeid Mahmoodizadeh; Ali Esmaeily
Abstract
Extended Abstract Introduction Information obtained from change detection processes in urban regions has a remarkable effect on urban planning and management. Due to the variety of land coversin urban regions, they are considered as a complex region extracting information from which is quite challengeable. ...
Read More
Extended Abstract Introduction Information obtained from change detection processes in urban regions has a remarkable effect on urban planning and management. Due to the variety of land coversin urban regions, they are considered as a complex region extracting information from which is quite challengeable. Hence, independent application ofoptical and radar data in changedetection may result in improper recognition of some altered regions and falsification ofobtained results. These two sensors record different kinds of information from different phenomenonat the earth’s surface, and thus can be considered as complementing each other. So, the fusion of these two data sources (radar and optical) can improve the detection of altered area. Radar data do not depend on the sun and atmospheric conditions and has thus gained much attention. In fact, radar data provide information on the spatial and geometrical characteristics of the geographical features, while optical sensors are sensitive to the reflectance of different surfaces at visible and infrared wavelengths.Therefore, the surface reaction is different in optical and radar data. Application of radar data in urban regions is limited merely due to the dependence of the intensity data (i) on the incidence angle and the speckle noise.On the other hand, independent application of optical data cannot produce accurate results in urban regions due to the spectral similarity of materials. And since the nature of these two types of images is different, it seems that their fusion improves and increases the accuracy of the information collectedfrom urban areas. Materials and Methodology Considering thebenefits of optical and radar data integrationas well as the application of unsupervised techniques in change detection studies, the present research has developed an unsupervised method for the integration of optical and radar data in order to detect changes. The area under study is a region located in the northwestof Mashhad city in northeastern Iran which has experienced considerable changes in its land cover from 2016 to 2018. Optical and radar dataare used toevaluate the proposed method. Optical data consists of a pair of multispectral imagesacquired from Sentinel-2 in 9/2016 and 9/2018. Radar data consists of a pair of SAR imagesacquired from Sentinel-1 in 9/2016 and 9/2018. The proposed method was used to integrate radar and optical data with the aim of obtaining a single band image with a higher information content. This method is an effective solution used to integrate data and reduce data dimensions from n to one dimension. In this method, necessary preprocessing was first performed on the radar and optical data, and then the characteristics extracted from optical and radar images were integratedpixel-to-pixel. technique was used to integrate these characteristics and detect changes. Generally in this method, input is divided into two categories of radar and optical data. The optical characteristics include spectral indices calculated from different bands at t1 and t2. These indices include NDVI, ARVI, SAVI, NDWI, NDBI, which are efficient for studying and identifying three types of land cover: vegetation, water and residential areas. In fact, to reduce the effects of topography and image brightness and to increase the possibility of detecting and segregating geographical features, the spectral indices were used as the input of optical part. Normalized ratio images obtained from the VV and VH polarizations of the radar images at t1 and t2 were considered as the input of radar data part. Then, a weight was estimated for each feature entering the segment using the PSO algorithm. Since the present study seeks to estimate the optimal weight of characteristics extracted from optical and radar images and ultimately to combine these features and obtain a single-band image, each particle in this algorithm contains the n weight of the extracted features from the images. OTSU thresholding techniquewhich is the relation used for inter-class variance maximization is also used as thecost function to assess the particles. In this function, the weight of each characteristic should be selected in a way that the inter-class (two classes of altered and unaltered regions)variancereaches its maximum value and the most optimal threshold limit can be estimated. The output of the proposed method will be a single-band image with higher information content. After applying the OTSU threshold limit, two classesof altered and unaltered regions are formed. The proposed method was also compared with other unsupervised change detection methods. Results Findings of the present study indicate high efficiency and accuracy of the method developed for changedetection. In this method, the ratio of pixels wronglydetected to the total number of evaluated pixels was 9.21% which is the lowest value. The overall accuracy and Kappa coefficients of the classification were respectively 90.79 and 0.819, which were the highest values compared to the other methods used in the present study. Conclusion Considering the benefits of optical and radar data integration, as well as unsupervised techniques application in change detection study, the present research has developed an unsupervised method for integration of optical and radar data andchangedetection. This unsupervised method for data integration is usedto achieve a single band image with higher information content. The technique makes it possible to integrate the optical and radar data and reduce data dimensions from n to one. For all input characteristics entering section, a weight was estimated using PSO algorithm. Since the proposed method is unsupervised, OTSU thresholding technique which is the relation used for inter-class variance maximization, is also used to assess the particles. The results have revealed high capability of the proposed method todetectchanges witha higher accuracy.
Mohsen Shaterian; Seyed Hojjat Mousavi; Zahra Momenbeik
Abstract
Extended Abstract Introduction Knowing type and percentage of each land use and land cover are considered to be a fundamental need for understanding and managing an area. Given the ever-increasing changes in land use, managers and experts need to be aware of past changes and developments. This is because, ...
Read More
Extended Abstract Introduction Knowing type and percentage of each land use and land cover are considered to be a fundamental need for understanding and managing an area. Given the ever-increasing changes in land use, managers and experts need to be aware of past changes and developments. This is because, policy making and solving existing problems require detecting changes and determining the trend of changes over time. Satellite data is one of the quickest and least expensive methods available based on which researchers can produce different land use map. In this regard, Landsat Satellite imageries are one of the most important data sources used to study different types of land use and land cover changes, such as deforestation, agricultural expansion and urban growth. Extracting information from satellite imagery through classification is one of the most widely used methods. One of the most important applications of remote sensing data is for investigating and discovering changes in phenomena with a spatial-temporal nature (i.e. phenomena whose position and status changes over time). In fact, change detection is the process of identifying and determining the type and extent of land cover or land use in a given period of time based on remote sensing images. The present study seeks to monitor land use changes in Shahr-e Kord during the period of 1985 to 2017, and to prepare land use maps of the area using Landsat satellite imageries. Materials & Methods In the present study, satellite imageries received from TM, ETM+, and OLI sensors of Landsat satellites in 1985, 2000, 2015, and 2017 were extracted from the United States Geological Survey (www.usgs.gov) and analyzed using different remote sensing software and geographical information systems like ENVI 4.7 and ArcGIS 10.4. In order to produce land use changes map, error correction was first performed. Then, images were processed using supervised classification method and maximum likelihood algorithm, which based on previous studies have a higher accuracy compared to other algorithms. In order to classify land use/land covers, a training sample was produced for each land use based on field observations, topographic maps (1:25000) produced by Iran National Cartographic Center, Google Earth imageries, and visual study of the imageries. Then, classification results were corrected using auxiliary data, visual interpretation, experiential knowledge, and GIS techniques. Prior familiarity with the region, visual study of imageries, previous experience and field operations revealed that following land uses exist in the region and are detachable on the images as well: a) urban, b) agricultural, c) industrial, d) meadow, e) airport, and c) other land uses (including pasture, rocky areas and areas without any specific land cover). Confusion or error matrix –including overall accuracy, producer’s accuracy, user accuracy and kappa coefficient- was also used to evaluate the accuracy of the classification. Also, urban land use changes were monitored using image differentiation functions. Results & Discussion After production of land use maps based on imageries received in 1985, 2000, 2015, and 2017, area of the six land cover classes was obtained. Results indicate that during these four periods (1985 to 2000), urban, industrial, agricultural and airport land uses have increased to 13, 111.7, 5.2 and 3.4 km2 (1.26, 10.16, 0.51 and 0.4 % increase) respectively, while meadows and other land uses have faced a decreasing trend. In other words, it can be concluded that most changes during this 15-year period occurred in meadows and other land uses. Since development of the airport have resulted in destruction of a large part of meadows, this land use have faced more severe changes. Land use changes from 1985 to 2017 indicate that 7.8 km2 of agricultural lands were transformed into urban land use, 1.4 km2 to industrial land use, 1.08 km2 to airport and 7.7 km2 to other land uses. Also, 20.5 km2 of other land uses were transformed into urban land use, 203.1 km2 to agricultural land use, 0.03 km2 to dried meadows, 0.17 km2 to airport and 14.5 km2 to industrial land use. 2.8 km2 of meadows were also transformed into agricultural land use, 0.05 km2 to industrial land use and 2.04 km2 to airport. During this period, urban and industrial land uses have remained unchanged. Conclusion Generally, results indicate that urban, industrial and agricultural land uses have developed over time, and these land uses have always had a positive increasing trend. While meadows and other land uses have had a decreasing and negative trend. This is due to the construction of Shahr-e Kord Airport, uncontrolled exploitations, digging wells and drought phenomena, which have led to a decrease in the level of water in aquifers and destruction of natural ecosystem in this region. In this way, previous meadows have turned into the source of intense dust generation in the city, which is a sign of desertification and ecosystem destruction. Due to drought and water scarcity in recent years, new deep wells have been dug with the aim of supplying water. This have occurred despite the critical condition of the meadows, and thus, have resulted in repeated protests by farmers and livestock farmers. Dramatic decrease in other land uses, including pastures, can also be attributed to recent droughts in Iran and intense dust generation. Increased population, increased human pressure on natural resources and also development of agricultural lands are among other causes of the present situation. Based on existing maps and satellite imageries, Shahr-e Kord is developing towards North and North West. In some areas, this development has occurred in pastures. Therefore, due to very high population density in the region which is still increasing, and also ongoing migration of villagers to the city, supplying appropriate accommodation and occupation for this population requires finding new suitable locations for urban and industrial development of the city. This development process should happen with correct management and according to the goals of sustainable development.
Kamran Karimi; Gholamreza Zehtabian; Marzban Faramarzi; Hassan Khosravi
Abstract
Extended Abstract Introduction Land use changes is a widespread and accelerating process, mainly driven by natural phenomena and anthropogenic activities, which in turn drive changes that would impact natural ecosystem. Because of the human population growth and its impacts, land-use patterns are changing ...
Read More
Extended Abstract Introduction Land use changes is a widespread and accelerating process, mainly driven by natural phenomena and anthropogenic activities, which in turn drive changes that would impact natural ecosystem. Because of the human population growth and its impacts, land-use patterns are changing very fast. Most of the population in Iran depends on agriculture, so the land use changes are mostly linked to agricultural developments. In recent decades, rapid land use changes have been associated with the degradation of natural resources, especially in sensitive ecosystems. On the other hand, like many other developing countries in the world, significant land-cover changes have been occurred in Iran within two last centuries. These changes were primarily due to human activities in connection with the population increase, which forced people to clear forest for cultivation and other activities. This study tries to present the effect of irrigation systems on land use changes since over three decades. Methodology Abbas plain with a surface area of 34104 ha, is located in Ilam province near the Iran’s western border. The average of annual precipitation and temperature are 207mm and 26.1o respectively. Karkheh dam, one of the largest soil dams in the world and the largest soil dam in Iran and the Middle East, located 15 km east of Abbas plain. The Karkheh Dam is designed to irrigate 320,000 hectares of downstream land including Abbas plain. The water transfer project to the Abbas plain was launched in May 2005. In the present study area, changes in land cover were evaluated in the pre and after- exploitation period of irrigation networks of Karkheh dam to the Abbas plain in Ilam province, Iran. To obtain more accurate results, Landsat sensors imagery of TM, ETM + and OLI were used for the years of 1989, 2003 and 2013, as well as topographic maps, Google Earth images and area coverage. To classify the land use changes, supervised classification method with maximum likelihood algorithm was applied in the ENVI4.8 software. Images of all three periods were classified into five classes: rangelands, agricultural land, residential land, river bed and barren lands and hill moor. In order to determine more precisely changes, areas were obtained for two other periods. Results The classification accuracy results showed that the Kappa line was more than 87% for every three years and the overall accuracy obtained were 90.43%, 92.28% and 94.76% respectively for these years. The results also showed that barren lands and hill moor class has covered the largest area of this study place during the two periods (pre and after- exploitation), so that, it was 12344.1 hectares in the first period and 17370.5 hectares in the second one. In both study periods, the rangeland class has been destroyed, but in the second period 13.8% was destroyed more than the first one. Due to the exploitation of irrigation systems by farmers in the second period, more changes in land use have been converted to agricultural use, so that, 3671.8 hectares (55%) have been added to these lands during 10 years. The growth of residential areas was 0.27% of the study area after channelling, which was estimated 1.6 times higher than the first one. The area increase average in this class is 10.2 hectares per year. The most frequent conversion to farm use was barren lands and hill moor class. These lands have undergone a change by residents of the region due to their location between agricultural lands and a short distance from irrigation systems. A large number of land use changes can be prevented by defining the scope for agricultural land. Conclusion and Discussion In the present study area, irrigation has been in practice since over 25 years ago. Significant land-use changes have occurred in the study area in response to the Karkheh Dam from time to time affecting agricultural productivity leading to land-use changes. Unfortunately, some parts of these changes are out of schedule and unskillful and, that is significant for planners to know about these. All in all, for providing management activities and environmental programmes, accurate data on land use changes are essential. Satellite images and maximum likelihood algorithm provide the baseline data essential for proper understanding on the land-use patterns in the past and its impacts. It is also proper to understand the past land use changes ratio, and the physical and socio-economic factors behind.
Seyyed Hojjat Mousavi; Abolfazl Ranjbar; Mehdi Haseli
Abstract
Due to the changesin land use that is done mostly by human activities, changedetection of landuse and assessment of their environmental impact isessential for future planning and managing the resources. Therefore, the aim of this research is monitoring, detecting andtrending the landuse changes in Abarkooh ...
Read More
Due to the changesin land use that is done mostly by human activities, changedetection of landuse and assessment of their environmental impact isessential for future planning and managing the resources. Therefore, the aim of this research is monitoring, detecting andtrending the landuse changes in Abarkooh basin (1976-2014) in orderto assess the environmental issues such as human stress onearth without considering tolerance capacity, and to identify the regions havingenvironmental stress.In this regard, after classification to identify the type of land uses and applying the base component analysis and tasseled cap functions and difference of images, satellite images data from Landsat, MSS (1976), TM (1990), ETM + (2000 and 2006) and OLI (2014)) sensors, and remote sensing techniques such as supervisory classification and accuracy assessment have been used to monitor the land use changes. The classification results indicate the enhancing of seven typesof land uses including urban lands, agricultural lands, wastelands, rocky lands, rangelands, clayey plain anddesert, and which have the highest accuracy of classification in 2014with kappa coefficient values of82.18%and total accuracy of 0.76. The trending results of changes in land use indicate an upward trend of the area in rangelands (5.65%), rockylands (2.52%),wastelands (3.63%) and agricultural lands (1.04%), and a downward trendof the area in urban land (4.33%), clayey plain (6.89%) and desert (6.03%). From the perspective of base component analysisand tasseled cap functions, 1.748% (306.4912 km2) and 3.989% (699.961 KM2) of the area of the study region were faced with increasing changes of landuse, and in general, the overall trend of the changes of increasing classes is upward. Most of the changes in land use are destructive and devastating, and in terms of spatial changes correspond to the area around human community centers suchas Abarkooh and Mehrdasht cities. It is evident that,due to the continuationof this trend, the Abarkooh basinbecomes a dead inactive ecosystem that lacksany ecological and biological production potential in the near future.
Vahid Sadeghi; Hamid Enayati; Hamid Ebadi
Abstract
Analyzing multi-temporal remotelysensed images is an effective technique for detecting land useand land cover changes in urban areas. Apart from thetechnique used to detect the changes, the features space has an enormous impact on the accuracy of the results. Achieving satisfactory results in detecting ...
Read More
Analyzing multi-temporal remotelysensed images is an effective technique for detecting land useand land cover changes in urban areas. Apart from thetechnique used to detect the changes, the features space has an enormous impact on the accuracy of the results. Achieving satisfactory results in detecting changes inurban areasrequires the use of optimal spectral and spatial features (texture). Although global search is the only guarantees of achieving the optimal set of features, but it is a very timely and impractical process in practice. Data reduction techniquessuch as PCA considers the independence of the data tofind a smaller set of variables with less redundancy withoutintending to improve the CD accuracy. Difficulty in setting thebest threshold for JM distance in Separability Analysis Algorithm (SAA)reduces its efficiency. The main purpose of this paper is to select the optimaltextural and spectral features to enhance the CD accuracy usinggenetic algorithms (GA) and Bayesian classifier. To investigate the effectivenessof the proposed tecknique, a case study using IRS-P6and GeoEye1 satellite imagery taken from Sahand New Town (Northwest ofIran on July 15, 2006, andSeptember 1, 2013) was performed. All of the aforementioned methods of feature selection (PCA, SAA and proposed GA-based method) were implemented in MATLABR2013a. The results show that, textural features provides a complementary sourceof data for CD in urban areas. The results show thatfeature selection is an effective process fordetecting changes basedon textural and spectral features. Each of the techniques for selecting features has its own limitations and advantages, but in general, improve the CD accuracy. The proposed GA-based feature selectionapproach was found to be relatively effective when compared withPCA and SSA approaches. Overall accuracy and Kappa coefficient ofCD were increased from 53.66% to 88.49% and 58.94% to90.39%respectivelyusing proposed methods compared tothe use of spectral information.
Saleh Arekhi
Abstract
The face of the earth is always changing due to human activities and natural phenomena. Therefore, in order to optimize the management of the natural areas, knowledge of the ratio of land cover / land use changes is considered necessary.The present study was conducted to detect changes in land cover/land ...
Read More
The face of the earth is always changing due to human activities and natural phenomena. Therefore, in order to optimize the management of the natural areas, knowledge of the ratio of land cover / land use changes is considered necessary.The present study was conducted to detect changes in land cover/land use in Abdanan region over a period of 25 years. In order to carry out the research, images of the years of 1985, 2000 and 2010 from TM, ETM + and TM sensors of Landsat satellite were used, and the map of the change detection was prepared and the final results was presented after performing the necessary corrections in the preprocessing stage, by the object-oriented classification of the images in the IdrisiSelvi software environment.The results show that during the period from 1985 to 2010, we are witnessing the decreasing trend of lands with moderate and good rangeland cover, which indicates the general trend of destruction in the region through the replacement of moderate and good pastures by the uses of poor pasture and barren lands. The extracted coefficients of validity assessment (total accuracy and kappa coefficient of 95% and 94% respectively) indicate the high accuracy of this classification method.
According to the results obtained from this research, it is suggested that the object-oriented classification method to be used in the preparation of land cover / land use maps and also the detection of changes.
Maliheh Sadat Madanian; Alireza Sofianian
Volume 21, Issue 82 , September 2012, , Pages 44-49
Abstract
Change detection is the process of identifying changes in an object or phenomenon by observing it in different time intervals. Careful and timely detection of changes in land forms and reliefs provides a better basis for understanding relations and the interactions between human and natural phenomena. ...
Read More
Change detection is the process of identifying changes in an object or phenomenon by observing it in different time intervals. Careful and timely detection of changes in land forms and reliefs provides a better basis for understanding relations and the interactions between human and natural phenomena. In this way, it makes managing and exploiting resources possible. Remote sensing data is a wonderful resource for different applications in detecting changes, due to its temporal magnification, spectral and radiometric variety, appropriate digital format and integrated view. Many methods have been developed to detect changes, all of which have advantages and disadvantages. According to the studies, these methods show different results in the same environment. Generally, change detection methods are classified into 3 different classes: pre-classification comparison, post- classification comparison, advanced methods. The present article analyzes some of these methods like image subtraction, image division, main components analysis, detection of controlled changes, and detection of uncontrolled changes, hybrid, artificial neural networks, vegetation-impermeable surfaces-soil model and geographic information systems. Pre-classification methods detect changes caused by multi-temporal data without producing classified vegetation and land-use maps. Yet, post-classification methods provide a precise matrix of changes and they usually need input analysis. There are diverse advanced methods which are usually developed in response to specific studies. Studies indicate that image subtraction, main components analysis and post-classification methods are the most popular methods used for change detection. However in recent years, artificial neural networks and combinations of remote sensing and geographic information systems are regarded as important techniques.
