Mimarlık ve Şehir Planlama Bölümü Koleksiyonu
https://hdl.handle.net/20.500.12440/1110
2024-03-29T08:47:08Z
2024-03-29T08:47:08Z
Assessment of Rapid Urbanization Effects with Remote Sensing Techniques
Yagmur, Nur
Dervisoglu, Adalet
Bilgilioglu, B. Baha
https://hdl.handle.net/20.500.12440/5801
2023-02-09T11:36:16Z
2022-01-01T00:00:00Z
Assessment of Rapid Urbanization Effects with Remote Sensing Techniques
Yagmur, Nur; Dervisoglu, Adalet; Bilgilioglu, B. Baha
Istanbul is the most populous city in Turkey. The population, which was approximately 5.5 million in 1985, has reached 15.5 million in 2020. Population growth is the most important factor behind human activities that put pressure on the environment. An increasing population means depletion of limited resources, increasing environmental problems, and rapid urbanization. In parallel with the increase in population and urbanization, there has also been an increase in demand for housing, leading to new residential areas in almost every district of Istanbul. This study examined the transformation from vegetation areas to residential areas between 1985 and 2020 in a selected region in Buyukcekmece, one of the 39 districts of Istanbul. The relationship between land use and land cover (LULC) change in the area and Land Surface Temperature (LST) change caused by urbanization was analyzed. It is seen that the built-up area has increased from 57.1 ha to 781.4 ha in 35 years. In every five years, an increase in surface temperatures was determined in parallel with increasing urbanization, and this increase was determined as about 5.4℃ from 1985 to 2020. Also, when the temperature data of the Buyukcekmece Meteorological station is analyzed, it is seen that there has been an increase of approximately 2 ºC in air temperatures in the last five years. In addition, movements were observed in the stability of structures in rapid urbanization areas after analyzing with the PSI time series InSAR method. The main causes were determined as construction sites around the buildings and geological conditions of the ground, which are triggered by urbanization. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
2022-01-01T00:00:00Z
1 of 1 Satellite-derived shallow wetland bathymetry using different classification algorithms and datasets
Dervisoglu, A.
Bilgilioğlu, Burhan Baha
Yağmur, Nur
https://hdl.handle.net/20.500.12440/5617
2023-02-28T06:36:53Z
2021-01-01T00:00:00Z
1 of 1 Satellite-derived shallow wetland bathymetry using different classification algorithms and datasets
Dervisoglu, A.; Bilgilioğlu, Burhan Baha; Yağmur, Nur
Remote sensing (RS) effectively identifies, analyzes, and monitors wetlands. In addition to these two-dimensional studies, RS is used with several techniques in determining shallow water depths. The primary purpose of this study is to obtain shallow wetland bathymetry utilizing spectral reflections obtained at different water depths by field study and satellite images. Machine learning (ML) algorithms, which are widely used in remote sensing, are used in this study. Four algorithms were selected as random forest (RF), support vector machine (SVM), Neural Networks (NN), and Maximum Likelihood Classification (MLC). Since machine learning algorithms use training samples/datasets, the classification accuracy is directly related to selecting these data. The effect of pixel counts on classification was investigated by using two different training data set also. Duden (Kulu) Lake, which is a shallow wetland, was chosen as the study area. The Iterative Self-Organizing Data Analysis Technique (ISODATA) classification algorithm divided into as many clusters as possible was applied on Sentinel-2 multispectral images. All classes were redefined using measured spectral signatures and were created a bathymetric map. This map was used as reference data in creating training sets and the accuracy assessment of ML algorithms. When the water surface areas obtained from algorithms were compared with the bathymetric map and Normalized Difference Water Index, the best result was obtained with RF. According to the accuracy assessment results, it was seen that the number of training data affects the accuracy, and the best results were obtained with SVM and RF algorithms with training data containing more pixels (overall accuracy 93.87% and 92.64, kappa 0.89 and 0.87, respectively).
2021-01-01T00:00:00Z
Satellite-derived shallow wetland bathymetry using different classification algorithms and datasets
Bilgilioğlu, Burhan Baha
Dervisoglu, Adalet
Yagmur, Nur
https://hdl.handle.net/20.500.12440/5596
2023-01-30T07:21:50Z
2021-01-01T00:00:00Z
Satellite-derived shallow wetland bathymetry using different classification algorithms and datasets
Bilgilioğlu, Burhan Baha; Dervisoglu, Adalet; Yagmur, Nur
Remote sensing (RS) effectively identifies, analyzes, and monitors wetlands. In addition to these two-dimensional studies, RS is used with several techniques in determining shallow water depths. The primary purpose of this study is to obtain shallow wetland bathymetry utilizing spectral reflections obtained at different water depths by field study and satellite images. Machine learning (ML) algorithms, which are widely used in remote sensing, are used in this study. Four algorithms were selected as random forest (RF), support vector machine (SVM), Neural Networks (NN), and Maximum Likelihood Classification (MLC). Since machine learning algorithms use training samples/datasets, the classification accuracy is directly related to selecting these data. The effect of pixel counts on classification was investigated by using two different training data set also. Duden (Kulu) Lake, which is a shallow wetland, was chosen as the study area. The Iterative Self-Organizing Data Analysis Technique (ISODATA) classification algorithm divided into as many clusters as possible was applied on Sentinel-2 multispectral images. All classes were rede-fined using measured spectral signatures and were created a bathymetric map. This map was used as reference data in creating training sets and the accuracy assessment of ML algorithms. When the water surface areas obtained from algorithms were compared with the bathymetric map and Normalized Difference Water Index, the best result was obtained with RF. According to the accuracy assessment results, it was seen that the number of training data affects the accuracy, and the best results were obtained with SVM and RF algorithms with training data containing more pixels (overall accuracy 93.87% and 92.64, kappa 0.89 and 0.87, respectively). © 2021 Desalination Publications. All rights reserved.
2021-01-01T00:00:00Z
Satellite-derived shallow wetland bathymetry using different classification algorithms and datasets
Dervisoglu, Adalet
Yagmur, Nur
Bilgilioglu, Burhan Baha
https://hdl.handle.net/20.500.12440/5587
2023-03-30T12:29:36Z
2021-01-01T00:00:00Z
Satellite-derived shallow wetland bathymetry using different classification algorithms and datasets
Dervisoglu, Adalet; Yagmur, Nur; Bilgilioglu, Burhan Baha
Remote sensing (RS) effectively identifies, analyzes, and monitors wetlands. In addition to these two-dimensional studies, RS is used with several techniques in determining shallow water depths. The primary purpose of this study is to obtain shallow wetland bathymetry utilizing spectral reflections obtained at different water depths by field study and satellite images. Machine learning (ML) algorithms, which are widely used in remote sensing, are used in this study. Four algorithms were selected as random forest (RF), support vector machine (SVM), Neural Networks (NN), and Maximum Likelihood Classification (MLC). Since machine learning algorithms use training samples/datasets, the classification accuracy is directly related to selecting these data. The effect of pixel counts on classification was investigated by using two different training data set also. Duden (Kulu) Lake, which is a shallow wetland, was chosen as the study area. The Iterative Self-Organizing Data Analysis Technique (ISODATA) classification algorithm divided into as many clusters as possible was applied on Sentinel-2 multispectral images. All classes were rede-fined using measured spectral signatures and were created a bathymetric map. This map was used as reference data in creating training sets and the accuracy assessment of ML algorithms. When the water surface areas obtained from algorithms were compared with the bathymetric map and Normalized Difference Water Index, the best result was obtained with RF. According to the accuracy assessment results, it was seen that the number of training data affects the accuracy, and the best results were obtained with SVM and RF algorithms with training data containing more pixels (overall accuracy 93.87% and 92.64, kappa 0.89 and 0.87, respectively). © 2021 Desalination Publications. All rights reserved.
2021-01-01T00:00:00Z