Iranian Journal of Remote Sensing & GIS
Year:2021 | Volume:13 | Issue:1|Papers Count:7

In this study, the SAR data is used as a supplementary data to overcome the limitations of the multispectral (MS) image in building detection. Therefore, the proposed method utilizes a multisensor data fusion to take the advantages of both MS and SAR data together. In addition, two different filter-based feature selection methods, MNF and PCA, are investigated as an alternative scenario when the training data is not accessible. In this respect, the optimum feature vector is selected using MNF, PCA and Genetic methods from MS and SAR data, separately. Thereafter, each selected feature vector is used to classify the images by implementing the support vector machine (SVM) and the artificial neural network classification methods. The experimental result shows that the PCA is able to select the feature vector without the need of training data as well as genetic algorithm. However, the MS classification result is poor where both roofs and streets are covered with asphalt. In this framework, the fusion of SAR and MS images in feature level was utilized to improve the classification results. Finally, to assign a label at the sample, a majority voting is calculated between the used classification methods results. However, according to the noisy result, using the neighborhood information in the form of a moving spatial window in different sizes is examined to determine the label of the central pixel more accurately. According to the experimental results, the overall accuracy and building detection accuracy are obtained 92.82% and 80.14%, respectively, which represent the satisfying performance of the proposed method.

It is necessary to know about the quantity of urban tree canopy cover due to its role in air and noise pollution reduction, wind prevention, saving rain water, and runoff control. Being expensive and time consuming, the manual extraction of tree canopy has been replaced by remote sensing techniques conducted on the images, digitally. There are several parameters which must be optimized prior to use of object oriented classification. One of these parameters is Scale affecting the segmentation results, significantly. Scale is usually set by trial and error which is an experimental approach. One of the aims of this study is to optimize Scale parameter, automatically. In addition, after segmentation process based on a proper Scale, it is required to classify the identified segments based on the attributes which are extracted from these segments. In this stage, the selection of suitable classification method fed by the proper attributes is critical. In this research, LiDAR data and aerial image acquired on Vaihingen, Germany, were utilized for segmenting the urban area. In order to identify suitable attributes, random forest feature selection was applied on the attributes derived from the identified segments. Machine learning methods including support vector machine, random forest, and decision tree were compared for classifying the segments based on their suitable attributes into two classes including tree canopy cover and others. The results indicated that Scale of 25 is the best one to segment this area. Also, the tree canopy cover map derived from support vector machine with quality index of 79.90 showed the best performance among different classifiers used in this study.

Digital elevation models and its derivatives are important factors for watershed modeling. It is obvious that DEM errors adversely affect the accuracy and thereby modeling of natural processes. This problem along with the impossibility of measuring all elements of nature, has led to a major evolution in the way of understanding and explaining phenomena. In this way, we can use the fractal geometry with the theory that many natural phenomena are order in the chaos. Each element of nature is represented as a fractal geometry number. The fractal geometry is a quantitative tool for studying the geomorphology of drainage networks and modeling many complex natural phenomena. In fact, geophysical phenomena such as drainage networks are fractal phenomena with fractal behavior. The purpose of this paper is to evaluate sensitivity of the drainage networks based on DEMs (ASTER & SRTM), flow direction algorithms (Single Flow Direction (D8) and Multiple Flow Direction (MD8)) and topographic maps of 1:25000 in order to study the fractal dimension of drainage network on geological formations of Yazd-Ardakan basin. The results showed that the least difference in the length and the rank of the stream belonged to the drainage network obtained from the topographic maps of 1:25000. After the topographic maps, ASTER and the multi-flow direction (MFD) algorithm and ASTER, and the single flow direction (SFD) algorithm are close to real ground map. Even though the multi-flow direction algorithm shows more detail on the drainage network. But it is not close to real ground map. The difference is particularly noticeable in the first rank of streams. SRTM and the flow direction algorithms showed only good results in routing the main rank of drainage networks. In fact, the results of this study demonstrate that accurate extraction of drainage networks from DEMs generated by remote sensing technologies such as SRTM or ASTER and SFD or MFD algorithms remains challenging. Therefore, the analysis of DEMs and flow direction algorithms should be considered as an important part of hydrological and geomorphological research. Due to the very high sensitivity of the fractal dimension to the smallest change in drainage network conditions, the drainage network obtained from topographic maps were used to calculate the fractal dimension. The mean fractal dimension of 1.149, 1.16 and 1.207, respectively, represents Taft, Granite and Kahar formations. There is a significant correlation between fractal dimension and sensitivity to erosion of geological formations (level 0.99). In fact, the fractal dimension increases with increasing the sensitivity to erosion along with the drainage density in geological formations. The results showed that fractal dimension allows for a quick and accurate analysis of sensitivity to erosion of the formations of this area.

Drought is one of the most important natural disasters in the country, with devastating environmental and economic effects. Most drought studies have focused on drought severity and other drought characteristics have not been usually investigated. In this research, for the first time, the capability of meteorological drought indices and satellite data are combined and applied to study drought in inland and coastal basins. For this purpose, the SPI index was calculated by using TRMM satellite precipitation products and then, the drought characteristics such as severity, duration, magnitude, and extent were spatially studied. The results showed that the correlation coefficient between the SPI calculated from the image and the station data was 0.94. The maximum intensity of drought in the study area was -4.19 which occurred in December 2010. Furthermore, the frequency of extreme droughts in 6- and 12-months timescales was higher in the inland area compared with the coastal area. Moreover, in the six-month timescales, 60 percent of drought events had a magnitude of -18.3 or less. The results showed that it is possible to obtain the extent of drought by using satellite imagery which cannot be calculated by other methods. Besides, by using satellite images, drought characteristics could be studied spatially at the basin scale, which is not possible by traditional methods. The results showed the advantage of using satellite precipitation images in the drought study

Colored dissolved organic matter (CDOM) is an important measure of water quality. CDOM can reduce the amount of light in water layers, disrupt the biological activity of photosynthesis, and inhibit the growth of phytoplankton populations that are essential for the aquatic food chain. Contrary to conducted research to date, which uses a specific wavelength, in this paper, we first examined the possibility of using visible portion of the spectrum to determine CDOM at 254-443 nm (254, 260, 350, 375, 400, 412, 440, 443 nm) in Landsat 8 . we then selected the most appropriate band ratios to measure CDOM at measurable wavelengths using the SVR algorithm (the parameters of which have been optimized using the genetic algorithm). It is noteworthy that in this study, the ratio of Coastal to red bands (), blue to red (), and the ratio of green to red bands () were considered for CDOM retrieval. Based on the results, considering the coefficient of determination ( = 0.71) and the amount of errors (MSE = 1.161 , RMSE = 1.077  and MAE = 0.946 ), it was concluded that the ratio of green to red bands in Landsat 8 is the most suitable choice for determining the colored dissolved organic matter. Moreover, according to the results from this study, the measurement of CDOM (440) is the most appropriate index for evaluating the quality of lake water resources in terms of their concentrations.

The study area is located in the northeast of neyriz and near the village of Ghori in Fars province. Geologically, the units of the study area are located in the zone-Sanandaj-Sirjan and with the general northwest-southeastern trend. Most of these Units calcareous units, units sericitic - chlorite schist and amphibolite units up. In this research, ASTER sensor images and ground magnetometric data were used to explore and identify iron-rich regions in the study area. In this investigation, we applied methods of False Color Composite (FCC), Band Ratio (BR), Principle Component Analysis (PCA) using ASTER images and areas with severe alterations propellitic, phyllic and sericite. Using methods of ground magnetometric processing, many methods containes reduce to pole (RTP), upward continuation, Analytic Signal, Tilt Angle, Vertical Derivative were used to identify the sources and we were able to identify the edges of these anomalies. In the study area, we were able to identify four anomalies under the ground that it is very important. The results of both methods explored four anomalies. Aster imager process and magnetometric data led to primary potential mineral map of the area. For credibility of results, 52 samples were taken and analyzed by XRD methods. Five boreholes have been drilled to a depth of 140 meters and all results are consistent with each other. The methods used are important and valuable

One of the most important modes of public transport is the metro transport network, which has a significant impact on reducing traffic and air pollution. On the other hand, due to the exorbitant costs of setting up the metro network, step-by-step development with the operation of one line and the implementation of other lines is of interest by urban managers. Therefore, the aim of this study is to investigate the extent of access to Isfahan metro network in the horizon of 1410 with the spatial equity approach from both horizontal and vertical aspects in 5 social classes using Gini coefficient indicators, Lorenz curve, service (supply) level index of public transportation and access. What distinguishes this research from the other similar studies is the investigation of access to the network of each metro line and finally all the lines and the estimation of population growth up to the horizon of 1410, which plays a significant role in the decisions of urban planners to develop other modes of urban transportation. The results of this study showed that Gini coefficients in access to the metro network in Isfahan in the study of horizontal equity are higher than the vertical equity, which shows a great injustice in the distribution of access of sensitive and needy groups to the metro network. So that the Gini coefficient in citizen's access to all lines in horizontal equity is 0.42 and in vertical equity in 5 classes including people over 60 years, under 15 years, without private cars, immigrants and households with an area of ​​less than 50 square meters are 0.45, 0.49, 0.5, 0.54 and 0.6, respectively