Over the past few decades, surface deformations have been observed and measured geodetically at m... more Over the past few decades, surface deformations have been observed and measured geodetically at many places all over the world, including Central and western Turkey. Surface deformations in some of these regions have been attributed to aseismic slip-on faults and/or to excessive pumping of groundwater. In this study, we present our investigation on the ground subsidence in Ödemiş town (W. Turkey) located in the Küçük (K.) Menderes Graben where one of the most severe and widespread surface fracturings has been reported. The entire graben is analyzed using the Sentinel-1 synthetic aperture radar (SAR) data with multi-temporal interferometric SAR techniques. A total of 342 single look complex products acquired in 2015–2018 are processed using the Small Baseline Subset method. Vertical mean velocity fields reveal that K. Menderes Graben is experiencing extensive subsidence at rates reaching as much as 29 cm/year, making it one of the fastest subsiding regions in the world. The spatial correlation between the subsiding regions and the unconsolidated sediments suggests that the subsidence is most probably due to over drafting of the groundwater, which is confirmed by the strong temporal correlation between displacement time series and groundwater level changes. Inelastic/elastic deformation ratios calculated for the entire graben suggest that inelastic deformation is the dominant component in the region, implying an irreversible deformation. Skeletal storage coefficients calculated at well locations also support the idea of inelastic deformation. However, severe inelasticity is not extensive, and the region may still recover from subsidence with correct groundwater management.
2020 28th Signal Processing and Communications Applications Conference (SIU), 2020
Surface deformations in Bolvadin town without any devastating earthquakes have been observed in t... more Surface deformations in Bolvadin town without any devastating earthquakes have been observed in the last 10 years. In this study, ground deformation analysis of Bolvadin region was performed by Sentinel-1 synthetic aperture radar (SAR) data and multi-temporal SAR interferometry (InSAR) method. Sentinel-1 images obtained between October 2014 and October 2018 in ascending and descending orbits were processed with SNAP and StaMPS softwares. Deformation velocity maps and vertical displacement time series were produced and compared with geology and groundwater level of the region. Deformation velocity maps show significant subsidence in the region. The most severe subsidence, up to 35 mm/year, was found in the southern part of Bolvadin which is characterized by the presence of soft alluvial deposits. Both in long and short term, there was a strong correlation between the subsidence and the groundwater level. As a result, the high correlation of the vertical deformation velocity with lith...
2019 9th International Conference on Recent Advances in Space Technologies (RAST), 2019
Urbanization has a dynamic structure especially in megacities and therefore rapid detection of th... more Urbanization has a dynamic structure especially in megacities and therefore rapid detection of the urban is vital for sustainable management of the city. In this work, we apply a multi-source feature data approach to investigate the urban area of Istanbul, Turkey which is a megacity with an approximate 15 million inhabitant, and under strong both anthropogenic and natural pressures. In order to analyse and compare the spatial pattern of the urban footprint, different techniques are applied. Speckle divergence, backscatter and repeat pass interferometric coherence values are considered for the analysis. To this aim, L-band HH and HV polarized ALOS-2 Synthetic Aperture Radar (SAR) data were acquired from Japan Space Exploration Agency's (JAXA). Pixel based Random Forest Classification method was used for the urban mapping. During the classification, different scenarios have been applied using speckle divergence, backscatter and coherence information. Overall, user and producer acc...
2017 25th Signal Processing and Communications Applications Conference (SIU), 2017
In this study, Sentinel-1A SAR imagery for land use/cover classification and its impacts on class... more In this study, Sentinel-1A SAR imagery for land use/cover classification and its impacts on classification algorithms were addressed. Sentinel-1A imagery has dual polarization (VV and VH) and freely available from ESA. Istanbul was selected as the study region. After the pre-processing steps including the applying the precise orbit file, calibration, multilooking, speckle filtering and terrain correction, the imagery was classified as the following step. Three classification algorithms (SVM, RF and K-NN) were implemented and the impacts of additional bands (VV-VH, VV+VH etc.) were investigated. Results demonstrated that highest classification accuracy of this study was obtained by SVM classification with the original bands (VV and VH) of Sentinel-1A imagery. Moreover, it was concluded that additional bands had different impacts on each classifier within accuracy.
2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), 2019
This study evaluates the impacts of three booster types (two tree-based and one linear model) in ... more This study evaluates the impacts of three booster types (two tree-based and one linear model) in extreme gradient boosting (XGBoost) for crop classification using multi-temporal PolSAR (Polarimetric Synthetic Aperture Radar) images. Ensemble learning algorithms have received great attention in remote sensing for classification due to their greater performance compared to single classifiers in terms of accuracy. Extreme gradient boosting is the regularized extension of traditional boosting techniques and could overcome the overfitting constrain of gradient boosting (a.k.a gradient boosting machine). Three types of booster which are linear booster, tree booster and DART (Dropouts meet Multiple Additive Regression Trees) booster were tested on XGBoost for crop classification. From the multi-temporal PolSAR data, two types of polarimetric dataset (linear backscatter coefficients and Cloude–Pottier decomposed parameters) were extracted and incorporated into the classification step. The impacts of polarimetric features for crop classification were also analyzed in detailed besides exploring the boosting types of XGBoost. Our experimental results demonstrated that tree booster and DART booster were found to be superior compared the linear booster in terms of overall classification accuracy for both polarimetric dataset. The highest classification accuracy (87.97%) was achieved by tree booster with linear backscatter coefficients. Furthermore, linear backscatter coefficients achieved higher performance with respect to Cloude–Pottier decomposition in terms of classification accuracy.
2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), 2019
Investigation of radar and optical data indices that contain a lot more information on landscapes... more Investigation of radar and optical data indices that contain a lot more information on landscapes and vegetation dynamics can be useful to identify opportunities and challenges in agricultural activities. In addition, the potential of synchronous implications of radar and optical data will be an effective method for agro-environmental monitoring and management to promote economic and environmental sustainability as monitoring programs. Crop discrimination as an agricultural monitoring system is a critical step regarding to estimate the area allocated to each crop type, computing statistics for crop control of area-based subsidies or crop production forecasting, environmental impact analysis and some other applications. Integrating both optical (reflectance) and Synthetic Aperture Radar (backscatter) multi-temporal features provides some advantages in terms of a more reliable crop map. We utilize multi-temporal Sentinel-1 Synthetic Aperture Radar (SAR) imagery and Sentinel-2 optical datasets in order to investigate the performance of the sensors backscatter and reflectance for temporal crop type mapping and the sustainable management of agricultural activities. Multi-temporal Sentinel-1, C-band VV and VH polarized SAR data and Sentinel2 optical data were acquired simultaneously by in-situ measurements for the study area. As preliminary results, it is concluded that the classification accuracies were improved results (5%) with using combinations of sensors. Classification accuracies of 93% were achieved in this study with integration use of SAR and optical data.
Information extraction through remote sensing data is important for policy and decision makers as... more Information extraction through remote sensing data is important for policy and decision makers as extracted information provide base layers for many application of real world. Classification of remotely sensed data is the one of the most common methods of extracting information however it is still a challenging issue because several factors are affecting the accuracy of the classification. Resolution of the imagery, number and homogeneity of land cover classes, purity of training data and characteristic of adopted classifiers are just some of these challenging factors. Object based image classification has some superiority than pixel based classification for high resolution images since it uses geometry and structure information besides spectral information. Vegetation indices are also commonly used for the classification process since it provides additional spectral information for vegetation, forestry and agricultural areas. In this study, the impacts of the Normalized Difference Vegetation Index (NDVI) and Normalized Difference Red Edge Index (NDRE) on the classification accuracy of RapidEye imagery were investigated. Object based Support Vector Machines were implemented for the classification of crop types for the study area located in Aegean region of Turkey. Results demonstrated that the incorporation of NDRE increase the classification accuracy from 79,96% to 86,80% as overall accuracy, however NDVI decrease the classification accuracy from 79,96% to 78,90%. Moreover it is proven than object based classification with RapidEye data give promising results for crop type mapping and analysis.
2017 25th Signal Processing and Communications Applications Conference (SIU), 2017
In this study, L-band ALOS PALSAR radar satellite image and Landsat TM optical satellite image we... more In this study, L-band ALOS PALSAR radar satellite image and Landsat TM optical satellite image were used to investigate the contribution of radar satellite image to optical satellite image for land cover mapping. Dual-polarimetric data of ALOS satellite and also normalized difference vegetation index (NDVl) generated from Landsat image were used for the analysis. In addition, different classification techniques were taken into consideration and forest dominated land cover maps were produced and the results were compared. Random Forest (RF), k-Nearest Neighbors (k-NN) and Support Vector Machines (SVM) approaches were applied as image classification techniques. While the best result among the methods is DVM, the data set in which combined data are used gives the best general accuracy result.
Oil release into the ocean may affect marine ecosystems and cause environmental pollution. Thus, ... more Oil release into the ocean may affect marine ecosystems and cause environmental pollution. Thus, oil spill detection and identification becomes critical important. Characterized by synoptic view over large regions, remote sensing has been proved to be a reliable tool for oil spill detection. Synthetic Aperture Radar (SAR) imagery show returned signal that clearly distinguish oil from oil-free surface under optimal wind conditions, which makes it the most frequent used remote sensing technique in oil spill detection, but there is also have a number of oceanographic and atmospheric phenomena that also shows dark signature at SAR images will easily be mistaken with oil spill signatures. In this study five diferent classifier (Logistic regression, Linear Bayes Normal Classifier, Quadratic Bayes Normal Classifier, K-Nearest Neighbor Classifier, Przen Windows) provided by matlab PRTolls will be tried on TerraSAR data and the results will be compared. First of all feature set will be defin...
2018 26th Signal Processing and Communications Applications Conference (SIU), 2018
In this study, the classification accuracies of four different classification methods with two ba... more In this study, the classification accuracies of four different classification methods with two balanced and two imbalanced data sets for the classification of Sentinel-1B SAR (Synthetic Aperture Radar) data were comparatively evaluated and the impacts of training data sets into the accuracy were investigated. In some circumstances, it is possible to collect high number of ground truth samples for some classes however not possible for some other classes which are represented by less number of ground truth samples. In such cases, the imbalanced data set is the issue. Supervised classifiers, by its nature, employ many different input parameters in consideration of the decision surface separating the two classes. More than the classification model itself, purity, size and allocation of ground truth samples as well as the adaptation between the training data and adopted classifier are of key importance in accuracy of image classification. In our study, two parametric (Naïve Bayes and Lin...
Accurate and reliable information regarding crop yields and soil conditions of agricultural field... more Accurate and reliable information regarding crop yields and soil conditions of agricultural fields are essential for the sustainable management of agricultural areas. The increasing necessity of the food due to the high population, global climate change and rapid urbanisation, the sustainable management of the agricultural resources is becoming more crucial for countries. Remote sensing technology offers a feasible solution for gathering the cost-effective, reliable and up-to-date information about crop monitoring by using high-resolution remote sensing data. Image classification is the one of most common method to obtain information from the remotely sensed images. Despite machine learning based classifiers such as Support Vector Machines (SVM) could provide high classification accuracy, the researchers have been still working to improve the classification accuracy. Recently, the utilisation of ensemble learning approaches in remote sensing classification is the research of interest for this purpose. In this study, we implemented six different supervised classification techniques and a classifier ensemble: Maximum Likelihood, Mahalanobis Distance, Minimum Distance, Spectral Angle Mapper, Parallelepiped, Support Vector Machines and Winnertakes- all (WTA) classification which is an ensemble based classifier. In this study, we investigated the comparative performance of the classifiers within overall and corn-class category for the study area located in Aydin, Turkey. Radial Basis Function (RBF) kernel was used here for the SVM classification. Results demonstrate that WTA classification outperformed other classification methods whilst the Parallelepiped obtained the lowest classification accuracy 13.24%. Moreover SVM gave the second highest overall classification accuracy of 89.90%
ISPRS International Journal of Geo-Information, 2019
In terms of providing various scattering mechanisms, polarimetric target decompositions provide c... more In terms of providing various scattering mechanisms, polarimetric target decompositions provide certain benefits for the interpretation of PolSAR images. This paper tested the capabilities of different polarimetric target decompositions in crop classification, while using a recently launched ensemble learning algorithm—namely Light Gradient Boosting Machine (LightGBM). For the classification of different crops (maize, potato, wheat, sunflower, and alfalfa) in the test site, multi-temporal polarimetric C-band RADARSAT-2 images were acquired over an agricultural area near Konya, Turkey. Four different decomposition models (Cloude–Pottier, Freeman–Durden, Van Zyl, and Yamaguchi) were employed to evaluate polarimetric target decomposition for crop classification. Besides the polarimetric target decomposed parameters, the original polarimetric features (linear backscatter coefficients, coherency, and covariance matrices) were also incorporated for crop classification. The experimental re...
Morphological changes, caused by the erosion and deposition processes due to water discharge and ... more Morphological changes, caused by the erosion and deposition processes due to water discharge and sediment flux occur, in the banks along the river channels and in the estuaries. Flow rate is one of the most important factors that can change river morphology. The geometric shapes of the meanders and the river flow parameters are crucial components in the areas where erosion or deposition occurs in the meandering rivers. Extreme precipitation triggers erosion on the slopes, which causes significant morphological changes in large areas during and after the event. The flow and sediment amount observed in a river basin with extreme precipitation increases and exceeds the long-term average value. Hereby, erosion severity can be determined by performing spatial analyses on remotely sensed imagery acquired before and after an extreme precipitation event. Changes of erosion and deposition along the river channels and overspill channels can be examined by comparing multi-temporal Unmanned Aer...
Over the past few decades, surface deformations have been observed and measured geodetically at m... more Over the past few decades, surface deformations have been observed and measured geodetically at many places all over the world, including Central and western Turkey. Surface deformations in some of these regions have been attributed to aseismic slip-on faults and/or to excessive pumping of groundwater. In this study, we present our investigation on the ground subsidence in Ödemiş town (W. Turkey) located in the Küçük (K.) Menderes Graben where one of the most severe and widespread surface fracturings has been reported. The entire graben is analyzed using the Sentinel-1 synthetic aperture radar (SAR) data with multi-temporal interferometric SAR techniques. A total of 342 single look complex products acquired in 2015–2018 are processed using the Small Baseline Subset method. Vertical mean velocity fields reveal that K. Menderes Graben is experiencing extensive subsidence at rates reaching as much as 29 cm/year, making it one of the fastest subsiding regions in the world. The spatial correlation between the subsiding regions and the unconsolidated sediments suggests that the subsidence is most probably due to over drafting of the groundwater, which is confirmed by the strong temporal correlation between displacement time series and groundwater level changes. Inelastic/elastic deformation ratios calculated for the entire graben suggest that inelastic deformation is the dominant component in the region, implying an irreversible deformation. Skeletal storage coefficients calculated at well locations also support the idea of inelastic deformation. However, severe inelasticity is not extensive, and the region may still recover from subsidence with correct groundwater management.
2020 28th Signal Processing and Communications Applications Conference (SIU), 2020
Surface deformations in Bolvadin town without any devastating earthquakes have been observed in t... more Surface deformations in Bolvadin town without any devastating earthquakes have been observed in the last 10 years. In this study, ground deformation analysis of Bolvadin region was performed by Sentinel-1 synthetic aperture radar (SAR) data and multi-temporal SAR interferometry (InSAR) method. Sentinel-1 images obtained between October 2014 and October 2018 in ascending and descending orbits were processed with SNAP and StaMPS softwares. Deformation velocity maps and vertical displacement time series were produced and compared with geology and groundwater level of the region. Deformation velocity maps show significant subsidence in the region. The most severe subsidence, up to 35 mm/year, was found in the southern part of Bolvadin which is characterized by the presence of soft alluvial deposits. Both in long and short term, there was a strong correlation between the subsidence and the groundwater level. As a result, the high correlation of the vertical deformation velocity with lith...
2019 9th International Conference on Recent Advances in Space Technologies (RAST), 2019
Urbanization has a dynamic structure especially in megacities and therefore rapid detection of th... more Urbanization has a dynamic structure especially in megacities and therefore rapid detection of the urban is vital for sustainable management of the city. In this work, we apply a multi-source feature data approach to investigate the urban area of Istanbul, Turkey which is a megacity with an approximate 15 million inhabitant, and under strong both anthropogenic and natural pressures. In order to analyse and compare the spatial pattern of the urban footprint, different techniques are applied. Speckle divergence, backscatter and repeat pass interferometric coherence values are considered for the analysis. To this aim, L-band HH and HV polarized ALOS-2 Synthetic Aperture Radar (SAR) data were acquired from Japan Space Exploration Agency's (JAXA). Pixel based Random Forest Classification method was used for the urban mapping. During the classification, different scenarios have been applied using speckle divergence, backscatter and coherence information. Overall, user and producer acc...
2017 25th Signal Processing and Communications Applications Conference (SIU), 2017
In this study, Sentinel-1A SAR imagery for land use/cover classification and its impacts on class... more In this study, Sentinel-1A SAR imagery for land use/cover classification and its impacts on classification algorithms were addressed. Sentinel-1A imagery has dual polarization (VV and VH) and freely available from ESA. Istanbul was selected as the study region. After the pre-processing steps including the applying the precise orbit file, calibration, multilooking, speckle filtering and terrain correction, the imagery was classified as the following step. Three classification algorithms (SVM, RF and K-NN) were implemented and the impacts of additional bands (VV-VH, VV+VH etc.) were investigated. Results demonstrated that highest classification accuracy of this study was obtained by SVM classification with the original bands (VV and VH) of Sentinel-1A imagery. Moreover, it was concluded that additional bands had different impacts on each classifier within accuracy.
2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), 2019
This study evaluates the impacts of three booster types (two tree-based and one linear model) in ... more This study evaluates the impacts of three booster types (two tree-based and one linear model) in extreme gradient boosting (XGBoost) for crop classification using multi-temporal PolSAR (Polarimetric Synthetic Aperture Radar) images. Ensemble learning algorithms have received great attention in remote sensing for classification due to their greater performance compared to single classifiers in terms of accuracy. Extreme gradient boosting is the regularized extension of traditional boosting techniques and could overcome the overfitting constrain of gradient boosting (a.k.a gradient boosting machine). Three types of booster which are linear booster, tree booster and DART (Dropouts meet Multiple Additive Regression Trees) booster were tested on XGBoost for crop classification. From the multi-temporal PolSAR data, two types of polarimetric dataset (linear backscatter coefficients and Cloude–Pottier decomposed parameters) were extracted and incorporated into the classification step. The impacts of polarimetric features for crop classification were also analyzed in detailed besides exploring the boosting types of XGBoost. Our experimental results demonstrated that tree booster and DART booster were found to be superior compared the linear booster in terms of overall classification accuracy for both polarimetric dataset. The highest classification accuracy (87.97%) was achieved by tree booster with linear backscatter coefficients. Furthermore, linear backscatter coefficients achieved higher performance with respect to Cloude–Pottier decomposition in terms of classification accuracy.
2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), 2019
Investigation of radar and optical data indices that contain a lot more information on landscapes... more Investigation of radar and optical data indices that contain a lot more information on landscapes and vegetation dynamics can be useful to identify opportunities and challenges in agricultural activities. In addition, the potential of synchronous implications of radar and optical data will be an effective method for agro-environmental monitoring and management to promote economic and environmental sustainability as monitoring programs. Crop discrimination as an agricultural monitoring system is a critical step regarding to estimate the area allocated to each crop type, computing statistics for crop control of area-based subsidies or crop production forecasting, environmental impact analysis and some other applications. Integrating both optical (reflectance) and Synthetic Aperture Radar (backscatter) multi-temporal features provides some advantages in terms of a more reliable crop map. We utilize multi-temporal Sentinel-1 Synthetic Aperture Radar (SAR) imagery and Sentinel-2 optical datasets in order to investigate the performance of the sensors backscatter and reflectance for temporal crop type mapping and the sustainable management of agricultural activities. Multi-temporal Sentinel-1, C-band VV and VH polarized SAR data and Sentinel2 optical data were acquired simultaneously by in-situ measurements for the study area. As preliminary results, it is concluded that the classification accuracies were improved results (5%) with using combinations of sensors. Classification accuracies of 93% were achieved in this study with integration use of SAR and optical data.
Information extraction through remote sensing data is important for policy and decision makers as... more Information extraction through remote sensing data is important for policy and decision makers as extracted information provide base layers for many application of real world. Classification of remotely sensed data is the one of the most common methods of extracting information however it is still a challenging issue because several factors are affecting the accuracy of the classification. Resolution of the imagery, number and homogeneity of land cover classes, purity of training data and characteristic of adopted classifiers are just some of these challenging factors. Object based image classification has some superiority than pixel based classification for high resolution images since it uses geometry and structure information besides spectral information. Vegetation indices are also commonly used for the classification process since it provides additional spectral information for vegetation, forestry and agricultural areas. In this study, the impacts of the Normalized Difference Vegetation Index (NDVI) and Normalized Difference Red Edge Index (NDRE) on the classification accuracy of RapidEye imagery were investigated. Object based Support Vector Machines were implemented for the classification of crop types for the study area located in Aegean region of Turkey. Results demonstrated that the incorporation of NDRE increase the classification accuracy from 79,96% to 86,80% as overall accuracy, however NDVI decrease the classification accuracy from 79,96% to 78,90%. Moreover it is proven than object based classification with RapidEye data give promising results for crop type mapping and analysis.
2017 25th Signal Processing and Communications Applications Conference (SIU), 2017
In this study, L-band ALOS PALSAR radar satellite image and Landsat TM optical satellite image we... more In this study, L-band ALOS PALSAR radar satellite image and Landsat TM optical satellite image were used to investigate the contribution of radar satellite image to optical satellite image for land cover mapping. Dual-polarimetric data of ALOS satellite and also normalized difference vegetation index (NDVl) generated from Landsat image were used for the analysis. In addition, different classification techniques were taken into consideration and forest dominated land cover maps were produced and the results were compared. Random Forest (RF), k-Nearest Neighbors (k-NN) and Support Vector Machines (SVM) approaches were applied as image classification techniques. While the best result among the methods is DVM, the data set in which combined data are used gives the best general accuracy result.
Oil release into the ocean may affect marine ecosystems and cause environmental pollution. Thus, ... more Oil release into the ocean may affect marine ecosystems and cause environmental pollution. Thus, oil spill detection and identification becomes critical important. Characterized by synoptic view over large regions, remote sensing has been proved to be a reliable tool for oil spill detection. Synthetic Aperture Radar (SAR) imagery show returned signal that clearly distinguish oil from oil-free surface under optimal wind conditions, which makes it the most frequent used remote sensing technique in oil spill detection, but there is also have a number of oceanographic and atmospheric phenomena that also shows dark signature at SAR images will easily be mistaken with oil spill signatures. In this study five diferent classifier (Logistic regression, Linear Bayes Normal Classifier, Quadratic Bayes Normal Classifier, K-Nearest Neighbor Classifier, Przen Windows) provided by matlab PRTolls will be tried on TerraSAR data and the results will be compared. First of all feature set will be defin...
2018 26th Signal Processing and Communications Applications Conference (SIU), 2018
In this study, the classification accuracies of four different classification methods with two ba... more In this study, the classification accuracies of four different classification methods with two balanced and two imbalanced data sets for the classification of Sentinel-1B SAR (Synthetic Aperture Radar) data were comparatively evaluated and the impacts of training data sets into the accuracy were investigated. In some circumstances, it is possible to collect high number of ground truth samples for some classes however not possible for some other classes which are represented by less number of ground truth samples. In such cases, the imbalanced data set is the issue. Supervised classifiers, by its nature, employ many different input parameters in consideration of the decision surface separating the two classes. More than the classification model itself, purity, size and allocation of ground truth samples as well as the adaptation between the training data and adopted classifier are of key importance in accuracy of image classification. In our study, two parametric (Naïve Bayes and Lin...
Accurate and reliable information regarding crop yields and soil conditions of agricultural field... more Accurate and reliable information regarding crop yields and soil conditions of agricultural fields are essential for the sustainable management of agricultural areas. The increasing necessity of the food due to the high population, global climate change and rapid urbanisation, the sustainable management of the agricultural resources is becoming more crucial for countries. Remote sensing technology offers a feasible solution for gathering the cost-effective, reliable and up-to-date information about crop monitoring by using high-resolution remote sensing data. Image classification is the one of most common method to obtain information from the remotely sensed images. Despite machine learning based classifiers such as Support Vector Machines (SVM) could provide high classification accuracy, the researchers have been still working to improve the classification accuracy. Recently, the utilisation of ensemble learning approaches in remote sensing classification is the research of interest for this purpose. In this study, we implemented six different supervised classification techniques and a classifier ensemble: Maximum Likelihood, Mahalanobis Distance, Minimum Distance, Spectral Angle Mapper, Parallelepiped, Support Vector Machines and Winnertakes- all (WTA) classification which is an ensemble based classifier. In this study, we investigated the comparative performance of the classifiers within overall and corn-class category for the study area located in Aydin, Turkey. Radial Basis Function (RBF) kernel was used here for the SVM classification. Results demonstrate that WTA classification outperformed other classification methods whilst the Parallelepiped obtained the lowest classification accuracy 13.24%. Moreover SVM gave the second highest overall classification accuracy of 89.90%
ISPRS International Journal of Geo-Information, 2019
In terms of providing various scattering mechanisms, polarimetric target decompositions provide c... more In terms of providing various scattering mechanisms, polarimetric target decompositions provide certain benefits for the interpretation of PolSAR images. This paper tested the capabilities of different polarimetric target decompositions in crop classification, while using a recently launched ensemble learning algorithm—namely Light Gradient Boosting Machine (LightGBM). For the classification of different crops (maize, potato, wheat, sunflower, and alfalfa) in the test site, multi-temporal polarimetric C-band RADARSAT-2 images were acquired over an agricultural area near Konya, Turkey. Four different decomposition models (Cloude–Pottier, Freeman–Durden, Van Zyl, and Yamaguchi) were employed to evaluate polarimetric target decomposition for crop classification. Besides the polarimetric target decomposed parameters, the original polarimetric features (linear backscatter coefficients, coherency, and covariance matrices) were also incorporated for crop classification. The experimental re...
Morphological changes, caused by the erosion and deposition processes due to water discharge and ... more Morphological changes, caused by the erosion and deposition processes due to water discharge and sediment flux occur, in the banks along the river channels and in the estuaries. Flow rate is one of the most important factors that can change river morphology. The geometric shapes of the meanders and the river flow parameters are crucial components in the areas where erosion or deposition occurs in the meandering rivers. Extreme precipitation triggers erosion on the slopes, which causes significant morphological changes in large areas during and after the event. The flow and sediment amount observed in a river basin with extreme precipitation increases and exceeds the long-term average value. Hereby, erosion severity can be determined by performing spatial analyses on remotely sensed imagery acquired before and after an extreme precipitation event. Changes of erosion and deposition along the river channels and overspill channels can be examined by comparing multi-temporal Unmanned Aer...
Uploads
Papers