Harita Mühendisliği Bölümü Yayın Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/11494/320

Listeleniyor 1 - 20 / 127

Yusufeli Barajı su tutma sonrası arazi örtüsü değişimlerinin Google Earth engine ile analizi
(Halil AKINCI, 2025) Saralıoğlu, Ekrem; Alahmed, Baker
Bu çalışma, Türkiye’nin en yüksek barajı olan Yusufeli Barajı’nın tamamlanması ve su tutulmaya başlanması sonrasında meydana gelen arazi örtüsü değişimlerini incelemeyi amaçlamaktadır. Araştırma, uzaktan algılama teknikleri ve Google Earth Engine (GEE) platformu kullanılarak gerçekleştirmiştir. GEE, büyük ölçekli uydu görüntülerinin işlenmesi ve analiz edilmesi için güçlü bir araç olup, bu çalışmada arazi örtüsü değişimlerini hızlı ve etkili bir şekilde tespit etmek için kullanılmıştır. Çalışma kapsamında, en fazla %1 bulutluluğa sahip 2020 ve 2024 yılına ait Sentinel-2 görüntüleri kullanılmıştır. Çalışmada Normalize Edilmiş Fark Su İndeksi (Normalized Difference Water Index (NDWI)) ile değişim analizi, her iki görüntünün Destek Vektör Makineleri (DVM) ile sınıflandırılması, arazi kullanım sınıfları üzerinden analiz çalışmaları gerçekleştirilmiştir. 2020 ve 2024 yıllarına ait Sentinel-2 görüntülerinin DVM ile sınıflandırılması sırasıyla %93.74 ve %92.36 genel doğruluk ile gerçekleştirilmiştir. Yapılan değişim analizleri sonucunda 2020-2024 yılları arasında Çoruh Nehri’nin yüzey alanında 2632.11 ha’lık artış ve su altında kalan en büyük alanları orman toprağı, kayalık ve taşlık alanlar ile iskân alanlarının oluşturduğu tespit edilmiştir.
Türkiye’deki il yolları için Yıllık Ortalama Günlük Trafik (YOGT) tahmininde makine öğrenmesi algoritmalarının karşılaştırmalı analizi
(Niğde Ömer Halisdemir Üniversitesi, 2025) Biçici, Serkan
Yıllık Ortalama Günlük Trafik (YOGT), bir yoldan bir yıl boyunca geçen ortalama araç sayısını ifade etmektedir. Türkiye’de YOGT verileri Karayolları Genel Müdürlüğü tarafından üç farklı idari yol sınıfı için toplanmaktadır. Devlet ve otoyollar için YOGT verisi her yıl düzenli olarak elde edilmekte, ancak il yolları için bu veri genellikle üç veya dört yılda bir toplanmaktadır. Bu çalışmada, il yolları için YOGT tahmini amacıyla yedi farklı makine öğrenmesi algoritması kullanılmış ve performansları karşılaştırılmıştır. Yolun karakteristik özellikleri, diğer ulaşım sistemleriyle ilişkisini ve yol çevresinin demografik/sosyo-ekonomik özelliklerini yansıtan değişkenler kullanılmıştır. Rastgele orman ve destek vektör regresyonu algoritmaları en başarılı sonuçları vermiştir. Yolun karakteristik özellikleri ile demografik/sosyo-ekonomik faktörleri temsil eden değişkenlerin YOGT tahminleri üzerindeki etkisinin, diğer ulaşım sistemleri merkezleriyle olan ilişkileri yansıtan değişkenlere kıyasla çok daha belirleyici olduğu bulunmuştur.
Leveraging knowledge graphs and semantic web technologies for validating 3D city models
(TAYLOR & FRANCIS LTD, 2025) Akın, Alper Tunga; Usta, Ziya; Stoter, Jantien; Arroyo Ohori, Ken; Cömert, Çetin
The widespread use of three-dimensional (3D) city data plays a significant role in various applications, such as mixed reality, infrastructure facility management, solar potential analysis, navigation, and so on. Ensuring high spatial and semantic quality in these endeavours is crucial to gathering proper results. Ensuring quality means verifying that the data adheres to relevant standards. Although these relevant standards are openly published, there are issues with the names of interoperability and reusability in academic studies and software development efforts. In this study, these issues are addressed using semantic web technologies. Most 3D city models (3DCMs) are treated as knowledge graphs (KG) with this approach. The main contribution of the study is a web-based interoperable tool for validation of CityGML Level of Detail 2 (LOD2) 3DCMs, which is compatible with relevant standards. Besides, an open-source 3DCM-to-KG converter and an open validation ontology are published as by-products while accomplishing the main goal. By virtue of the KG approach, the 3DCM KG becomes capable of carrying its own validation constraints, which come from the validation ontology. With these efforts, this study provides a practical, interoperable solution to improve the quality and usability of 3DCMs and validation plans, fostering consistency across applications while aligning with established standards in the field.
Solo demand, rising rents: how young singles shape urban housing costs
(Emerald Publishing, 2025) Çalışkan, Bilal; Usta, Ziya; Hatami, Masud
Purpose – This study investigates how the concentration of young single-person households (aged 24–35 years) influences small-unit rental prices in Istanbul’s fragmented housing market. Amid rapid demographic shifts and urban restructuring, this paper aims to provide robust causal evidence on the demand-side pressures driven by young singles in shaping rental dynamics, particularly in the increasingly competitive one-bedroom apartment segment. Design/methodology/approach – Using a novel cross-sectional data set covering 605 neighborhoods in Istanbul, this study applies a two-stage least squares instrumental variable strategy to address endogeneity, particularly simultaneity bias. The spatially lagged share of young singles is used as an instrument. The model controls for a rich set of neighborhood-level variables, including accessibility, amenities, income, education, population structure and housing stock age. Findings – A one-percentage-point increase in the share of young single-person households leads to a 4.2% increase in average rents for one-bedroom apartments. These effects are more pronounced in neighborhoods near employment centers, with strong transit access and lifestyle amenities. The results of this study emphasize that demographic clustering at the micro scale drives localized price inflation in the rental market and disproportionately burdens high-demand segments. Originality/value – To the best of the authors’ knowledge, this study is among the first to causally link neighborhood-level solo living patterns to rental inflation in emerging urban contexts. This study advances housing scholarship by segmenting the market by unit size and household structure, while offering policy-relevant insights for managing affordability. The findings of this study support a targeted small-unit housing strategy that responds to evolving demographic realities in dense metropolitan regions.
Kıyı alanlarının rekreasyonel amaçlı alternatif kullanımının Artvin örneğinde irdelenmesi
(Bartın Üniversitesi Orman Fakültesi, 2018) Arslan Muhacir, E. Seda; Yavuz Özalp, Ayşe
Geçmişten günümüze daima insanoğlunun ilgisini çeken kıyı alanları, rekreasyonel kullanım ve etkinlik çeşitliliği açısından oldukça zengin kaynak değerlerine sahiptir. Su kenarları, tarih boyunca yerleşim, ulaşım, rekreasyon ve turizm gibi çeşitli kullanım amaçlarına hizmet ederek ilgili amaçlar doğrultusunda planlanmış ve tasarlanmıştır. Bu bağlamda halkın kıyılardan aktif ve serbestçe yararlanması ve kıyı alanlarının sürdürülebilir kullanımı ve planlanmasına yönelik çalışmalar birçok araştırmanın hedefi olmuştur. Bu çalışmanın amacı, Artvin ilinin Karadeniz kıyısında yer alan Hopa ve Arhavi ilçelerine ait kıyı ve sahil şeridinin ilk bölümünde yer alan kullanımların yasal ve teknik açıdan irdelenerek kıyıların rekreasyonel kullanım potansiyelinin belirlenmesidir. Söz konusu çalışmada Artvin İli’ne ait toplamda 36,2 km olan kıyı bandı, idari sınırlar ve planlı/plansız alan durumu dikkate alınarak yedi bölüm altında ele alınmıştır. Çalışmada materyal olarak, 1/1000 ölçekli onaylı Uygulama İmar Planları, dolgu alanlarına yönelik hazırlanan planlar, 1/1000 ölçekli halihazır haritalar ve arazi çalışmalarıyla elde edilen veriler ve fotoğraflar kullanılmıştır. Çalışma alanındaki mevcut kıyı kullanımlarının belirlenmesi ve analizi ile haritaların üretilmesi ve düzenlenmesi sürecinde ise ArcMap 10.2, Google Earth ve Photoshop CS6 programlarından yararlanılmıştır. Yapılan tüm bu inceleme ve değerlendirmeler sonucunda, çalışma alanındaki arazi yapısının elverişsiz koşullarının, kıyı alanını ve dolayısıyla rekreasyonel kullanımı kısıtladığı, kıyının ve kıyının tamamlayıcısı olan sahil şeridinin yanlış alan kullanımlarına maruz kaldığı belirlenmiştir. Planlı alan kapsamındaki kıyı ve sahil şeridinde rekreasyonel amaçlı kullanımların var olduğu, bununla birlikte planlı alanların plansız alanlara nazaran daha çok yanlış kıyı kullanımlarına maruz kaldığı tespit edilmiştir. Ayrıca çalışma alanındaki kıyı genişliğinin, 0,5m ile 215 m arasında değiştiği ve çoğunlukla dar kıyı niteliği taşıdığı belirlenmiştir.
Investigating impacts of large dams on agricultural lands and determining alternative arable areas using GIS and AHP in Artvin, Turkey
(Selçuk Üniversitesi, 2017) Akıncı, Halil; Yavuz Özalp, Ayşe; Özalp, Mehmet
Large dams are generally built for the purposes of providing drinking or irrigation water, flood control, and producing hydroelectric power, but their constructions also result in some negative outcomes such as decreasing in flora and fauna diversity, inundation of arable lands, forest areas, cultural sites and involuntary displacement of people. The city of Artvin has been facing almost all of those negative effects since five large dams have being constructed on the section of the Çoruh River flowing within the city boundary. Three of those large dams completed submerged 795.60 ha of fertile agricultural land under the reservoir waters. The objective of this study was to determine potential suitable agricultural areas in substitution for those inundated due to these five dams. For this, the Analytic Hierarchy Process (AHP) method was used in this study. In the application, parameters including great soil groups, land use capability class, land use capability sub -class, soil depth, erosion degree, slope, aspect, elevation and other soil properties were used. A suitability map was created and separated into 5 categories according to the land suitability classification provided by the FAO. After deducting the forests, pastures, and reservoir areas, newly classified suitability map showed that 2.08% (11603.25 ha) of the study area was highly suitable, while 3.43% (19132.84 ha) was moderately suitable and 4.30% (23989.99 ha) was marginally suitable for agricultural production. It was interpreted that high slope, insufficient soil depth for agricultural production, and high erosion degree of the study area were effective factors in these findings.
Landslide susceptibility mapping of Canik (Samsun) district using bayesian probability and frequency ratio models
(Selçuk Üniversitesi, 2017) Akıncı, Halil; Doğan, Sedat; Kılıçoğlu, Cem
Landslides cause serious damage to infrastructure and property in many cities of Turkey, as well as the loss of life. Samsun is one of the cities where landslides are most frequently seen in Turkey. Most of the landslides occurred throughout the province, especially within the Atakum, Canik and İlkadım districts, have been described as natural disaster. In this study, the aim was to produce landslide susceptibility maps for one of these highly sensitive districts, Canik. For this purpose, the parameters of slope, aspect, altitude, topographic wetness index, profile and plan curvature, lithology, distance to drainage network and roads have been used in the landslide susceptibility analysis. Bayesian Probability (BP) and frequency ratio (FR) models have been used in the study. The areas in the produced susceptibility maps have been classified into five groups as “very low, low, moderate, high and very high susceptible”. The verification and control results revealed that the landslide susceptibility map generated using the BP model is more accurate than the FR model. At the same time, the very high and high susceptible areas in the landslide susceptibility map produced by BP model were compatible with the control landslides with a rate of 83.5%. These results indicated that the landslide susceptibility map generated using the BP model can be used for land use planning and landslide risk reduction studies.
Monitoring mass movements using Network-RTK measurement technique and producing potential rockfall scenarios in a paleo-landslide area
(SCIENDO, 2023) Kadi, Fatih; Akın, Alper Tunga; Usta, Ziya
Mass movements resulting from landslides cause significant losses in terms of lives and property. Periodic observations of these movements using geodetic measurement techniques help to prevent these losses. Network-RTK measurement technique produces real-time location with centimeter accuracy, based on phase observations using a network of reference stations. In this study, the paleo-landslide area in the Isiklar location of Trabzon province, Esiroglu district, Turkey, was chosen as the application area. This study aims to measure the application area between 2019 and 2021, using the Network-RTK technique to determine the mass movements. Additionally, there is a rock block in an area with a steep slope. The possible movement of this rock block is a threat to infrastructure facilities, residential areas, agricultural areas, and life safety if the mass movement continues. Within this scope, the potential movement scenarios of the block were produced using RocPro3D software and UAV photogrammetry. Scenarios following an ongoing mass movements in the region triggering another mass movement are discussed. In the light of the results obtained, mass movements in the vertical direction of up to 28 cm were detected in the area where the rock block is located in the last 2 years. The periodic continuation of mass movements in the study area, declared a disaster-prone area, confirms the importance of the rock block in the region. In another phase of the study, possible movement scenarios of the rock block were examined using a rockfall analysis. In this context, with the help of an unmanned aerial vehicle, a digital elevation model and orthophoto map of the region where the rock block is likely to move was produced and a base map to be used in rockfall analysis was obtained. As a result of the rockfall analysis, maps showing the speed, energy, spread, possible impacts, and stopping points were produced. With the examination of these maps, it has been determined that residential areas, agricultural areas, and infrastructure facilities in the study area may be significantly damaged.
Kentsel alanlarda 3B gölge analizi: Artvin Çoruh Üniversitesi örneği
(Halil AKINCI, 2025) Usta, Ziya
Kentsel alanlarda binaların oluşturduğu gölge etkisi özellikle güneş paneli kurulumu gibi uygulamalarda, kentsel mikroklima ve enerji verimliliği optimizasyonunda kritik bir role sahiptir. Geleneksel 2B analizlerin yetersizliği nedeniyle 3B gölge analizleri, binaların birbirine gölge oluşturma durumunun daha doğru tahmin edilmesini sağlar. Literatürde genellikle 2.5B modeller kullanılarak gölge analizleri yapılmıştır. Ancak bu modeller dikey yüzeylerin etkisini göz ardı etmektedir. Bu çalışmada 3B modeller kullanarak 3B gölge analizi yapılmıştır. 3B modelleme için prosedürel modelleme yöntemi kullanılmış, kat sayıları baz alınarak binalar LOD1 düzeyinde modellenmiştir. Işın İzleme (Ray-Tracing) algoritmasıyla güneşin günlük ve saatlik konumları dikkate alınarak gölge analizleri yapılmıştır. Artvin Çoruh Üniversitesi Seyitler ve Merkez Yerleşkelerinde binalar arası gölge etkisi düşük bulunmuştur. Ancak yakın mesafedeki yüksek binalar gölgeleme etkisi yaratmaktadır. Çatılardan sonra özellikle güney cephelerinin anlamlı düzeyde güneş ışığı aldığı belirlenmiş olup, bu da dış cephelerin de güneş paneli kurulum potansiyeli olduğunu ortaya koymaktadır. Bu çalışma, 3B gölge analizinin kentsel planlama süreçlerinde önemli bir araç olduğunu göstermektedir. Çalışmada elde edilen diğer önemli bir sonuç, analizlerin sadece çatıları değil dış cepheleri de kapsaması gerektiğidir. Bu sayede bina yüzeylerinden maksimum oranda yararlanılarak sürdürülebilir kentsel gelişim ve doğru yer seçimi sağlanabilir.
Analitik hiyerarşi yöntemi ile en uygun okul yer seçim analizi: Elazığ merkez örneği
(Halil AKINCI, 2025) Durdağ, Utkan Mustafa; Şen, Mehmet Sait; Usta, Ziya
Ülkemizde meydana gelen depremler Elazığ ilini de ciddi şekilde etkileyerek birçok eğitim kurumunun ağır hasar görmesine ve yıkılmasına yol açmıştır. Bu durum, yeni yapılacak okul alanlarının daha uygun ve güvenli yerlerde inşa edilmesi gerekliliğini bir kez daha gündeme getirmiştir. Bu çalışmada, çalışma alanı için 15 uygun kriter belirlenerek Elazığ İli Merkez İlçesi için en uygun okul alanlarının tespit edilmesi hedeflenmiştir. Çalışmada, ÇKKV (Çok Kriterli Karar Verme)yöntemlerinden Analitik Hiyerarşi Yöntemi (AHY) kullanılarak belirlenen kriterlerin ağırlıkları hesaplanmıştır. Ağırlık değerlerine göre, nüfus(%19), mevcut okullara yakınlık(%16) ve dere yataklarına uzaklık(%13) kriterleri toplam ağırlığın yaklaşık yarısını oluşturarak en etkili faktörler olurken, yüksek basınçlı doğalgaz hattına uzaklık(%1) ve yönlenme(%1) en az etkili kriterler arasında yer almıştır. CBS yardımıyla oluşturulan kriter haritaları kullanılarak ağırlıklı çakıştırma analizi gerçekleştirilmiş ve uygunluk haritaları elde edilmiştir. Bu haritalar aracılığıyla en uygun okul alanları tespit edilmiş, ayrıca mevcut okul alanlarının uygunluk durumları değerlendirilmiştir. Sonuçlara göre, çalışma alanının %95,93’ü uygun olmayan alanlar, %2,02’si az uygun alanlar, %1,99’u uygun alanlar ve %0,05’i çok uygun alanlar olarak sınıflandırılmıştır. Çalışma sonucunda elde edilen veriler, gelecekte okul planlaması ve yer seçiminde yol gösterici olabilecek niteliktedir.
Monitoring the changes of Lake Uluabat Ramsar site and its surroundings in the 1985-2021 period using RS and GIS methods
(Global NEST, 2023) Topal, T U; Memişoğlu Baykal, Tuğba
Ramsar sites are important ecosystems that are protected by international status, have great value in terms of biodiversity, and constitute a resource in terms of economic, cultural, scientific and recreational aspects. In this study, the change of Lake Uluabat Ramsar Site and its surroundings, between the years 1985-2021 has been observed. For this, Remote Sensing (RS) and Geographic Information Systems (GIS) methods were used. Vegetation change in the lake and its surroundings in 1985, 2000, 2015 and 2021 with Normalized Difference Vegetation Index (NDVI), and changes in water surfaces with the water indices Normalized Difference Water Index (NDWI) and Modified Normalized Difference Water Index (mNDWI) were analyzed by using Landsat multi-band satellite images (Landsat 5 TM, Landsat 7 ETM and Landsat 8 OLI/TIRS) as RS data. The resulting changes were monitored and the success of the indices in determining these areas and the relations of the indices with each other were questioned by Accuracy index, Kappa coefficent, and Correlation analyses. The results show 36-year long-term changes and reveal a 13.06% shrinkage of Uluabat Lake wetland and surrounding water areas with the highest kappa coefficients for mNDWI as 0.83, 0.90, 0.93, 0.97, respectively, over the years studied.
Evaluation of land suitability for olive (Olea europaea L.) cultivation using the random forest algorithm
(MDPI, 2023) Yavuz Özalp, Ayşe; Akıncı, Halil
Many large dams built on the Çoruh River have resulted in the inundation of olive groves in Artvin Province, Turkey. This research sets out to identify suitable locations for olive cultivation in Artvin using the random forest (RF) algorithm. A total of 575 plots currently listed in the Farmer Registration System, where olive cultivation is practiced, were used as inventory data in the training and validation of the RF model. In order to determine the areas where olive cultivation can be carried out, a land suitability map was created by taking into account 10 parameters including the average annual temperature, average annual precipitation, slope, aspect, land use capability class, land use capability sub-class, soil depth, other soil properties, solar radiation, and land cover. According to this map, an area of 53,994.57 hectares was detected as suitable for olive production within the study region. To validate the created model, the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) were utilized. As a result, the AUC value was determined to be 0.978, indicating that the RF method may be successfully used in determining suitable lands for olive cultivation in particular, as well as crop-based land suitability research in general.
Comparative analysis of tree-based ensemble learning algorithms for landslide susceptibility mapping: A case study in Rize, Turkey
(Multidisciplinary Digital Publishing Institute (MDPI), 2023) Yavuz Özalp, Ayşe; Akıncı, Halil; Zeybek, Mustafa
The Eastern Black Sea Region is regarded as the most prone to landslides in Turkey due to its geological, geographical, and climatic characteristics. Landslides in this region inflict both fatalities and significant economic damage. The main objective of this study was to create landslide susceptibility maps (LSMs) using tree-based ensemble learning algorithms for the Ardeşen and Fındıklı districts of Rize Province, which is the second-most-prone province in terms of landslides within the Eastern Black Sea Region, after Trabzon. In the study, Random Forest (RF), Gradient Boosting Machine (GBM), CatBoost, and Extreme Gradient Boosting (XGBoost) were used as tree-based machine learning algorithms. Thus, comparing the prediction performances of these algorithms was established as the second aim of the study. For this purpose, 14 conditioning factors were used to create LMSs. The conditioning factors are: lithology, altitude, land cover, aspect, slope, slope length and steepness factor (LS-factor), plan and profile curvatures, tree cover density, topographic position index, topographic wetness index, distance to drainage, distance to roads, and distance to faults. The total data set, which includes landslide and non-landslide pixels, was split into two parts: training data set (70%) and validation data set (30%). The area under the receiver operating characteristic curve (AUC-ROC) method was used to evaluate the prediction performances of the models. The AUC values showed that the CatBoost (AUC = 0.988) had the highest prediction performance, followed by XGBoost (AUC = 0.987), RF (AUC = 0.985), and GBM (ACU = 0.975) algorithms. Although the AUC values of the models were close to each other, the CatBoost performed slightly better than the other models. These results showed that especially CatBoost and XGBoost models can be used to reduce landslide damages in the study area.
Deep learning aided web-based procedural modelling of LOD2 city models
(Springer Science and Business Media Deutschland GmbH, 2023) Usta, Ziya; Akın, Alper Tunga; Cömert, Çetin
In a large variety of smart city applications, the processes are settled with LOD2 (Level of Details) and the generation of the LOD2 models requires the proper generation of the roof geometries. In general, obtaining roof type information and succeeding generations of the LOD2 models requires expensive aerial surveys and time-consuming construction processes. In this study, a methodology to generate LOD2 building models using only 2D building footprints and aerial imagery is explained to overcome these challenges. The roof type information has been obtained from an aerial image that covers the entire study area using a CNN (Convolutional Neural Network) model. Then, the roof geometries have been constructed procedurally by extending and implementing a well-known Straight Skeleton (SS) algorithm for three main types of roofs: flat, gable and hipped. These constructed roof geometries have been combined with LOD1 block models generated by extruding the 2D footprints according to the height attribute. The overall accuracy of the CNN is 89.9% and the class-wise accuracies are over 84% for all classes. The least recall value is observed for the gable roof class, the enhancement options are discussed in the relevant section. The proposed methodology has been developed as a web-based solution utilizing RESTful web services with modern web technologies. In summary, the main novelty of the study is based on two contributions: using DL for gathering roof-type information without any end-user interference and the extension of the SS algorithm for the construction of roof geometries. The final product of this study is a web-based architecture for the rapid generation of the LOD2 building models.
Conceptualizing spatial heterogeneity of urban composition impacts on precipitation within tropics
(Penerbit UTHM, 2023) Zakaria, Nur Hidayah; Asilah Ishak, Nur; Salleh, Siti Aekbal; Isa, Nurul Amirah; Suhana, Erniza; Gee Ooi, Maggie Chel; Abd.latif, Zulkiflee; Üstüner, Mustafa
Urban composition has exacerbated precipitation patterns. Rapid urbanization with dynamic composition and anthropogenic activities lead to the change of physical environment, especially land-use and land cover which subsequently magnifies the environmental effects such as flash floods, extreme lightning, and landslides. Due to extreme and elevated temperature trends with exacerbated rainfall patterns, these environmental effects become major issues in tropics. Albeit several studies pointed out that rapid urbanization induced precipitation, studies about the heterogeneity of urban composition on precipitation variables are still limited. Thus, this paper review studies about precipitation pattern in relation to the heterogeneity of urban composition that successfully integrates geographical information system (GIS) and remote sensing techniques to enhance the understanding of interactions between precipitation patterns against heterogeneity of urban composition. This article also addressed the current state of uncertainties and scarcity of data concerning remote sensing techniques. Evidently, with a comprehensive investigation and probing of the precipitation variables in the context of urbanization models fused with remote sensing and GIS, they put forward powerful set tools for geographic cognition and understand how its influence on spatial variation. Hence, this study indicated a great research opportunity to set the course of action in determining the magnitude of spatial heterogeneity of an urban composition towards the pattern of precipitation.
Investigation of landslide-based road surface deformation in mountainous areas with single period UAV data
(Taylor and Francis Ltd., 2022) Zeybek, Mustafa; Biçici, Serkan
Roads are an important role in the transportation and the economy. Therefore, roads should be constructed under geometric standards to increase service life and maximize safety. However, landslides occurring around the road, especially in mountainous regions, may cause deformation on the road surface. Generally, landslide areas can be detected by measuring in more than one period. The proposed methodology investigates the landslide effect in a single period and consists of the following steps. First, a UAV collects data to generate a 3 D model. Then, an appropriate road project is designed according to the road geometric standards and 3 D model. Finally, landslides are successfully determined by comparing the appropriate road design and the current state of the road. It is found that there are road subsidence and rising areas up to 20 cm. As a result, it was determined the landslide had significant effects on the road surface with single-period UAV data.
Building detection from high-resolution satellite images with faster regional based deep learning model
(Gumushane University, 2022) Saralioğlu, Ekrem; Güngör, Oğuz
Deep learning algorithms, which try to automatically learn features from a large data set to mimic the learning and analysis mechanism in the human brain, have sometimes started to be more successful than humans in solving problems that require high computation. The successful use of deep learning-based methods in various fields also increases its use in remote sensing. This study, it is aimed to make automatic building detection by deep learning from satellite images with high spatial resolution. First, a fused image with more spatial details was obtained by fusing the image to the high spatial resolution Worldview-2 satellite image. Then, the fused image of the study area was divided into parts, including the areas where building details are concentrated. The test and training data set was created by labeling the building objects in these image fragments. Finally, the Faster R-CNN model was trained with the prepared data set, enabling building detection from high spatial resolution satellite images. Building detection was performed with an average accuracy of 88.6% from high-resolution satellite image fragments containing fragments from different regions.
Classification of UAV point clouds by random forest machine learning algorithm
(Murat Yakar, 2021) Zeybek, Mustafa
Today, unmanned aerial vehicle (UAV)-based images have become an important data sources for researchers who deals with mapping from various disciplines on photogrammetry and remote sensing. Reconstruction of an area with three-dimensional (3D) point clouds from UAV-based images are an essential process to be used for traditional 2D cadastral maps or to produce a topographic maps. Point clouds should be classified since they subjected to various analyses for extraction for further information from direct point cloud data. Due to the high density of point clouds, data processing and gathering information makes the classification of point clouds a challenging task and may take a long time. Therefore, the classification processing allows an optimal solution to acquire valuable information. In this study, random forest machine learning algorithm for classification processing is applied with radiometric features (Red band, Green band and Blue band) and geometric characteristics derived from covariance feature (curvature, omnivariance, flatness, linearity, surface variance, anisotropy and normalized terrain surface) of points. In addition, the case study is presented in order to test applicability of the proposed methodology to acquire an accuracy and performance of random forest method on the UAV based point cloud. After the classification processing, a class assigned each point from the model was compared with the reference data class. Lastly, the overall accuracy of the classification was achieved as 96% and the Kappa index was reached to 91% on data set.
A review on pansharpening of multispectral images
(Gumushane University, 2021) Şerifoğlu Yılmaz, Çiğdem; Yılmaz, Volkan; Güngör, Oğuz
Remote sensing satellites cannot produce images of high spatial detail quality and spectral quality due to technical limitations in their sensors, which forces users to find alternative ways to produce such images. Pan-sharpening offers an effective solution to this problem. Pan-sharpening aims to transfer the spatial details of a high-resolution panchromatic image into a high spectral resolution image, producing a multispectral image of high spatial resolution. A wide variety of pansharpening methods have been proposed in the litreture. Each pansharpening method has its own advantages and disadvantages. This situation makes users hesitant about which method should be used under what situation. We believe that this study, whose primary objective is to provide theoretical information about various conventional and state-of-the-art pan-sharpening methods in the literature, and to guide the analysts as to which pansharpening methods should be used under what circumstances, will be a good pan-sharpening guide. This study also provides information on how the spatial and spectral quality of pan-sharpened images may be evaluated qualitatively and quantitatively.
Landslide monitoring and assessment for highway retaining wall: The case study of Taşkent(Turkey) landslide
(International Society for Photogrammetry and Remote Sensing, 2018) Zeybek, Mustafa; Şanloǧlu I.
Landslide monitoring and assessment of the highways retaining walls are a crucial task. Because there exist a risk and danger with regard to the movement of the wall to the highway by landslide force that may spread further. To evaluate the changing, movements have to be monitored. For this reason, we practised mobile LiDAR surveys on the landslide effected wall on the highway. The usage of the mobile LiDAR systems have significantly increased in recent years, especially for road management. Currently, mobile LiDAR technology is capable of measuring the earth surface with high precision and density as a 3D point clouds. As stated in this study, the point cloud data processing have been analysed further and the wall surface points fitted to a plane object for monitoring of the landslide effects. This study focuses on different plane fitting algorithms which represents the retaining wall, a performance assessment and evaluation of the deformation between two plane models. The analysis indicates that the uncertainty of the measurements between the two epochs on stable areas survey was within ±2 cm. According to the experimental results, the proposed methods performed promising results that can be used for monitoring of retaining walls for fast processing and assessment.

Güncel Gönderiler