Hasan Fathi Zad; Rashid Fallah Shamsi; Ali Mahdavi; Saleh Arekhi
Volume 22, Issue 1 , June 2015, , Pages 59-72
Abstract
Rangelands are one of the most important renewable resources and because of their extent and economic, social and distinctive environmental impacts are of very special importance. Unfortunately, in our country, like most developing countries, rangelands have been exposed to degradation for various reasons ...
Read More
Rangelands are one of the most important renewable resources and because of their extent and economic, social and distinctive environmental impacts are of very special importance. Unfortunately, in our country, like most developing countries, rangelands have been exposed to degradation for various reasons including the non-systematic management of these resources. Remote sensing technology and satellite data are useful tools in the studies of rangeland and vegetation sciences. One of the applications of satellite data is mapping range land use. The aim of this study was to compare two methods of maximum probability and fuzzy for rangeland zonation. For this purpose, Landsat ETM+ was used; then, after final geometric and radiometric corrections, the final classification map was prepared. According to the results of accuracy of these two methods using the kappa coefficient, the artificial neural network algorithm of fuzzy Artmap with a coefficient of 0.9614 was more accurate than the maximum probability algorithm with a coefficient of 0.8058. Results of this study also indicated that the traditional algorithms of classification such as statistical methods due to their low flexibility, and parametric types such as maximum probability method because of the dependence on the Gaussian statistics model, could not provide optimal results, when the samples were not normal. In this study, ENVI 4.5, Idrisi Andes 15 and Arc GIS9.3 software were used
Saleh Arekhi; Hasan Fathizad
Volume 21, Issue 3 , December 2014, , Pages 466-481
Abstract
Rapid land-use/land cover changes have taken place in many arid and semi-arid regions of Iran such as west of Iran over the last decades due to demographic pressure, agricultural pressure, government polices and environmental factors such as drought. This study was aimed to investigate the trends of ...
Read More
Rapid land-use/land cover changes have taken place in many arid and semi-arid regions of Iran such as west of Iran over the last decades due to demographic pressure, agricultural pressure, government polices and environmental factors such as drought. This study was aimed to investigate the trends of changes in the landscape, in Doiraj Watershed. In order to provide land cover maps, the satellite images of TM 1985, ETM+2000, ETM+2007 were applied and landscape metrics of class area, largest patch index, number and mean patch size, patch density and edge density were used to quantify landscape patterns. Various class-level landscape pattern metrics were calculated using FRAGTATS, in order to analyze landscape fragmentation. The results of landscape ecology change revealed that in this area during the first period (1985 - 2000), the area of forest lands decreased to 3,415 hectares, while the agricultural lands with 3514 hectares showed an increasing trend. On the other hand, the area of fair rangelands (20,440 hectares) showed a decreasing trend (in both periods) contrary to the area of poor rangelands, indicating the degradation process in the study area. Our results clearly showed that increased number of patches and decreased mean patch area were two important fragmentation indicators and the trend of landscape degradation and fragmentation was increasing. Therefore, the results necessitated paying attention to the quality of land use and cover in the region for decreasing the degradation of natural resources.
Saleh Arekhi; Mostafa Adibnejad
Volume 18, Issue 3 , September 2011, , Pages 420-440
Abstract
Land use classification using remotely sensed images is one of the most common applications in remote sensing, and many algorithms have been developed and applied for this purpose in the literature. This study investigates the efficiency of Support Vector Machines algorithms in image classification. ...
Read More
Land use classification using remotely sensed images is one of the most common applications in remote sensing, and many algorithms have been developed and applied for this purpose in the literature. This study investigates the efficiency of Support Vector Machines algorithms in image classification. Support Vector Machines (SVMs) are a group of supervised classification algorithms of machine learning that have been used in the remote sensing filed. The classification accuracy produced by SVMs may show variation depending on the choice of the kernel function. In this study, SVMs were used for land use classification of Ilam dam catchment using Land sat ETM+ data. The classification using SVM method was implemented automatically by using four kernel types, linear, polynomial, radial basis, sigmoid and the results were analyzed thoroughly. Results showed that SVMs, especially with use of radial, polynomial and linear function kernels, outperform the maximum likelihood classifier in terms of overall (about 10%) and kappa coefficient(about 15%) accuracies. So, this study verifies the efficiency and capability of SVMs in classification of remote sensed images.
Saleh Arekhi; yaghoub Niyazi
Volume 17, Issue 1 , September 2010, , Pages 74-93
Abstract
Presently, unplanned changes of land use have become a major problem. Most land use changes occur without a clear and logical planning with little attention to their environment impacts.Since that landuse change occurring over large areas, remote sensing technology is an essential and useful tool for ...
Read More
Presently, unplanned changes of land use have become a major problem. Most land use changes occur without a clear and logical planning with little attention to their environment impacts.Since that landuse change occurring over large areas, remote sensing technology is an essential and useful tool for landuse change detection. In this study,after applying geometric and radiometric correction on landsat images of TM(1988) and ETM+(2001) ,five techniques of change detection have been used in 80470 hectare in the region of Daresher,Ilam province. These change detection techniques included Image regression, NDVI differencing, Principal component analysis (PCA(, Tasselled cap (KT) and post-classification comparison. In all these techniques, following standarizing maps,change direction has been determined.The accuracy of the results obtained by each technique was evaluated by comparison with post-classification method through Kappa coefficient calculation. According to the results, NDVI differencing and PC2 differencing showed the largest accuracy with Kappa coefficients of 0.667 and 0.655, respectively.However, Different change detection algorithms have their own merits and no single approach is optimal and applicable to all cases. In practice, several change detection techniques should be used to implement change detection, whose results are then compared to identify the best approach through visual or quantitative assessment.
Saleh Arekhi
Volume 9, Issue 3 , September 2001, , Pages 1081-1098