Sürdürülebilir Kalkınma Amaçları
Yayınlar
- ArticleAçık Erişim2026Identifying Agricultural Crops with Similar Spectral Properties Using Machine Learning Classifiers and SenseFly eBee SQ Multispectral UAV Images
Akar, Özlem; Akar, Alper; Bayata, Halim Ferit
This study investigates the use of vegetation indices for accurately identifying crops with similar spectral characteristics as grapes, apricots, tomatoes, wheat, and clover for enhancing crop monitoring and management. A 59-hectare area in Karakaya Village, located in the Üzümlü district of Erzincan Province, Türkiye, was selected as the study area. This area contains crops with varying textures, object height, and spectral characteristics. In the study, multispectral (MS) images were acquired using the SenseFly eBee SQ unmanned aerial vehicle (UAV), and subsequently processed to generate an orthophoto, digital terrain model (DTM), and digital surface model (DSM). Fifteen vegetation indices, Gabor texture features, and object heights were integrated into MS bands. Crop classification was performed using two high-accuracy machine learning algorithms: Random Forest (RF) and Support Vector Machine (SVM). According to the overall classification accuracy results, the use of vegetation indices improved classification accuracy by 9% for RF and 5% for SVM. Incorporating Gabor texture features with the top-performing indices (MACARI1, OSAVI, ADVI, and DVI) further increased accuracy to 20% for RF and 12% for SVM. Additionally, including object height alongside the indices and Gabor features resulted in further accuracy gains of 10% and 11% for RF and SVM, respectively. F1-score, specificity, and accuracy analyses, along with various kappa statistics, also the significant improvements in classification performance. According to the McNemar test, the χ^2 values comparing orthophoto images with those incorporating indices, texture, and object height ranged from 6.353 to 35.556 for RF, and from 7.220 to 11.021 for SVM. Since all χ^2 values exceeded 3.84, the results indicate statistically significant improvements in the classification accuracy at the 95% confidence interval.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2026Scenario-based optimization of humanitarian supply chain distribution channels for a possible earthquake: a case study in Türkiye
Balkar, Oğuz Emre; Akar, Alper; Akar, Özlem
Earthquakes represent a serious risk to societies, economies, and critical infrastructure, highlighting the need for effective disaster preparedness and resilient humanitarian supply chains (HSCs). In seismically active regions such as Erzincan Province, Türkiye, HSC distribution networks must remain functional despite significant disruptions. This study proposes a five-stage mixed-method framework to design and optimize HSC distribution channels for a potential major earthquake in the central district of Erzincan. First, buildings and transportation links were evaluated in terms of seismic suitability to pre-select candidate main distribution centers (MDCs), local distribution points (LDPs), and low-risk routes. Proximity analyses were then conducted using Quantum GIS (QGIS) to identify potential LDPs within a 1–5 km service radius for 69 neighborhoods. These locations were further validated and optimized using Greenfield analyses in anyLogistix under a distance–demand cost minimization criterion. Four distribution channel scenarios were subsequently simulated over a two-month post-earthquake period in line with national and international disaster standards. Finally, the Shortest Path Method was applied to assign primary, secondary, and tertiary LDPs to each neighborhood. The results indicate that supplying nine LDPs (comprising schools and healthcare centers) through four MDCs, including a newly designated sports facility, minimizes transportation cost, travel distance, and lead time, while enabling 63.8% of neighborhoods to access their primary LDP within 3 km. The proposed framework offers a holistic approach by explicitly incorporating seismic compliance into the design of HSC distribution channels in earthquake-prone regions.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2024İmar Barışının Mera ve Yayla Alanlarındaki Yapılaşmaya Etkisinin İncelenmesi
Bayata, Halim Ferit; Akar, Alper; Akar, Özlem
Yayla ve meralar genellikle doğal yollarla oluşan bitki topluluklarıdır. Yapılan tahmini hesaplamalara göre, mera ekosistemleri dünya topraklarının yaklaşık %50' sini kapsamakta ve dünyadaki hayvanların yem ihtiyacının büyük bir kısmını karşılamaktadır. Yapılan çalışma ile, 2018 yılında yürürlüğe giren ve halk arasında imar barışı olarak adlandırılın 7143 sayılı yasanın, mera ve yayla alanlarında oluşabilecek kaçak yapılaşmaya olan etkisi araştırılmıştır. Çalışma alanı olarak Trabzon ili Akçaabat ilçesi sınırları içerisinde yer alan mera ve yaylalar seçilmiştir. Çalışmada Google Earth Pro programından elde edilen uydu görüntüleri ile Triplesat uydu görüntüleri kullanılarak zaman içerisinde meydana gelen kontrolsüz yapılaşma tespit edilmiştir. 1. çalışma bölgesinde 33 ve 2. çalışma bölgesinde 50 olmak üzere toplam 83 yeni yapının bu süre içerisinde yapıldığı belirlenmiştir. Elde edilen sonuçlar halen bu alanlarda kaçak yapılaşmanın devam ettiğini, denetlenme sürecinin hızlı ve etkili bir suretle yapılamadığını ve çıkarılan bu af niteliğindeki yasaların kaçak yapılaşmayı teşvik ettiğini göstermektedir.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2024Analysis of emergency assembly points for post-earthquake disaster management: a case study of Erzincan, Türkiye
Akar, Alper; Akar, Özlem; Konakoğlu, Berkant
The selection of emergency assembly points within the urban area holds significant importance for ensuring swift and effective intervention in the aftermath of a potential disaster until temporary shelter areas are prepared. In both historical and instrumental periods, Erzincan (Türkiye) has experienced major earthquakes resulting in significant loss of life and property. The likelihood of similar earthquakes occurring in Erzincan in the future remains high. Therefore, it is necessary to identify safe areas where people can assemble after an earthquake, moving away from hazardous zones. The aim of this study is to analyse the capacities and adequacies of emergency assembly points, which constitute a step in disaster management and enhance the earthquake resilience of the city, using Geographic Information Systems (GIS) based on selected criteria (accessibility, spatial distribution, proximity to healthcare facilities, size, capacity adequacy, and proximity to fault avoidance zones), and to propose solutions. The assessment revealed that the available assembly points are not homogeneously distributed throughout the city and are inadequate to meet the available building and population density. Therefore, in addition to the available 38 emergency assembly points, 67 new alternative emergency assembly points have been identified. The proposed emergency assembly points (in the 75–100% range) increased the number of neighborhoods within the 250 m service area by 43.75% and 42.5% for 500 m.The findings underscore the necessity for more comprehensive and effective planning for Erzincan in the event of a potential disaster or emergency.
RDL Kalıcı Kaydıİncele - ArticleYalnız künye2022Improving the accuracy of random forest-based land-use classification using fused images and digital surface models produced via different interpolation methods
Akar, Alper
Land-use maps produced with high accuracy are extremely important as a basis for better use of the land as they are widely utilized in many areas such as agricultural policies, natural resources management, and environmental operations. This study aimed to produce a high accuracy land-use map using digital surface models (DSMs) produced using different interpolation methods and a random forest (RF) classifier. High spatial resolution Triplesat-2 images, Worldview-2 (WV-2) images, and unmanned aerial vehicle (UAV) images were used in this study. First, DSMs were produced from the point cloud using different interpolation methods. The image fusion process was applied and these fused images were classified using an RF classifier together with the DSMs. Overall results showed that the DSM obtained by the kriging method yielded better results than the other methods by increasing the classification accuracy by 7%–13%. In addition, the McNemar test was applied to the images resulting from the classification of fused images with and without using DSMs to investigate the statistical significance of the differences. McNemar test demonstrated that the (Formula presented.) values were greater than 3.84, which revealed that the DSM produced via kriging interpolation had significantly increased the classification accuracy at a 95% confidence interval.
RDL Kalıcı Kaydıİncele - ArticleYalnız künye2022Prediction of geoid undulation using approaches based on GMDH, M5 model tree, MARS, GPR, and IDP
Konakoglu, Berkant; Akar, Alper
This study provides a comprehensive comparison of four different machine learning models including the group method of data handling (GMDH), M5 model tree (M5MT), multivariate adaptive regression spline (MARS), and Gaussian process regression (GPR) for predicting geoid undulation. For the first time, GMDH and M5MT were applied for this purpose. The obtained results were also compared with the classic inverse distance to a power (IDP) interpolation method. In order to assess the consistency of our results, two test sites with different topographic features were used for the evaluation of the models. In constructing the models, the geographic coordinate values and the geoid undulation value were used as inputs and output, respectively. Several statistical indices and rank analysis were used for evaluation of the models. According to the comparative results of all models in both test sites, the GMDH yielded the best performance among the developed models. The M5MT also exhibited acceptable results. Thus, it may be concluded that the proposed GMDH and M5MT have the potential to be alternative models that could assist geoscientists working with the geoid.
RDL Kalıcı Kaydıİncele - ArticleYalnız künye2022Prediction of geoid undulations: Random forest versus classic interpolation techniques
Akar, Alper; Konakoğlu, Berkant; Akar, Özlem
Local geoid determination studies are commonly carried out today to establish the relationship between the ellipsoidal height (Formula presented.) determined by satellite geodesy methods and the orthometric height (Formula presented.) found using geoid undulation (Formula presented.). The aim of this study was to determine a local geoid using the kriging, local polynomial (LP), and inverse distance to a power (IDP) interpolation methods along with the random forest (RF) regression method and to compare the performance. For the application, 193 Global Navigation Satellite System (GNSS)/leveling points homogeneously distributed over the study area were selected as reference data, and 70 GNSS/leveling points were selected as test data. The results were compared in terms of accuracy using well-known performance metrics, namely, the root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) values. According to the results, the highest R2 and the lowest RMSE and MAE values were obtained with the RF regression method. These findings demonstrated the superiority of the RF regression over the classic interpolation methods applied in the local geoid determination for the study area.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2021Investigation of the Effects of Tectonic Movements Occurring in Elazig and Surrounding Provinces on the Positions of TNPGN-Active Stations by Using Static Deformation Models
Konakoglu, Berkant; Akar, Alper
Turkish National Permanent GNSS Network-Active ( TNPGN-Active) Project serves their users with a total of 158 permanent stations, including the Turkish Republic of Northern Cyprus and Turkey. The movements caused by earthquakes can be determined effectively with this GNSS network. It was thought that the earthquakes, occurred on the Eastern Anatolian Fault Zone (DAFZ) on April 04, 2019 (5.2 MW), December 27, 2019 (4.8 MW) and January 24, 2020 (6.5 MW), affected TNPGN-Active stations located in neighbouring provinces close to this fault zone. In this context, a local GNSS network (ADY1, ARPK, BING, DIYB, ELAZ, ERGN, MALY, SIV1 and TNCE) were created from existing TNPGN-Active points and the movements of the stations in the network are periodically examined. theta(2) Criteria and IWST (Iterative Weighted Similarity Transformation), which were geodetic static deformation models, were used to determine movement amounts and directions. As a result of the evaluation, it was determined that both methods gave similar results. The largest movement was determined at the ELAZ station between the periods of January 03, 2019 and January 25, 2020 in the horizontal direction about 5.5 cm (southwest) and in the vertical direction about 3 cm (up). It was also determined that other TNPGN-Active stations were affected by the earthquake of 6.5 MW in particular on January 24, 2020 and there were movements in these stations up to 1-2 cm in horizontal direction.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2021Geoid undulation prediction using ANNs (RBFNN and GRNN), multiple linear regression (MLR), and interpolation methods: A comparative study; [Predicción de ondulación geoide con Redes Neuronales Artificiales (base radial y regresión generalizada), regresión lineal múltiple y métodos de interpolación: estudio comparativo]
Konakoglu, Berkant; Akar, Alper
This study evaluated different methods for geoid undulation prediction and included two types of artificial neural networks (ANNs)-the radial basis function neural network (RBFNN) and the generalized regression neural network (GRNN)-as well as conventional methods including multiple linear regression (MLR) and ten different interpolation techniques. In this work, k-fold cross-validation was used to evaluate the model and its behavior on the independent dataset. With this validation method, each of a k number of groups has the chance to be divided into training and testing data. The performances of the methods were evaluated in terms of the root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe efficiency coefficient (NSE), correlation coefficient (R2), and using graphical in-dicators. The evaluation of the performance of the datasets obtained using cross-validation was performed in two ways. When the method having the minimum error result was accepted as the most appropriate method, the natural neighbor (NN) gave better results than the other methods (RMSE = 0.142 m, MAE = 0.097 m, NSE = 0.98986, and R2 = 0.99011). On the other hand, it was observed that on average, the GRNN exhibited the best performance (RMSE = 0.185 m, MAE = 0.137 m, NSE = 0.98229, and R2 = 0.98249).
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2021Geoid undulation prediction using gaussian processes regression: A case study in a local region in Turkey
Konakoglu, Berkant; Akar, Alper
In order to convert ellipsoidal heights obtained by the Global Navigation Satellite System (GNSS) to orthometric heights, it is necessary to know the distance between the ellipsoidal and geoid surface, called the geoid undulation. The geoid undulation can be predicted using emerging mathematics tools and algorithms. The objective of this study was to develop a model for predicting the geoid undulation using Gaussian Process Regression (GPR), one of the soft machine learning algorithms having different covariance functions. This method was then compared with the radial basis function neural network (RBFNN), generalized regression neural network (GRNN), and the interpolation method of inverse distance to a power (IDP) with the power of 1, 2, 3, 4, and 5. First, 70 % of GNSS/leveling data (422 points) were used in the training phase. The remaining 185 points were used as testing data to check the effectiveness of the constructed model. In the GPR modeling, ten covariance functions (Materniso d= 1, 3, 5; Maternard d= 1, 3, 5; SEiso; SEard; RQiso; and RQard) were tested for prediction on this dataset. The GPR based on the Materniso (d = 1) covariance function model was introduced as an effective method for predicting geoid undulation and provided the best results (RMSE = 8.32 cm, MAE = 5.51 cm, R2 = 0.98968) when compared with the other developed GPR models. In addition, the statistical findings showed that the accuracy of all the GPR models was also better in predicting geoid undulation than the RBFNN, GRNN, and IDP with the power of 1, 2, 3, 4, and 5.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2020Investigation of the Effect of Elazig-Sivrice Earthquake on the Locations of TUSAGA-Active Stations with Web Based GPS Software
Konakoglu, Berkant; Akar, Alper
TNPGN-Active (Turkey National Permanent GNSS Network-Active) system, which placed the Republic of Turkey and KKTC with 158 fixed GNSS (Global Navigation Satellite System) station is available for commercial and academic studies. On January 24, 2020, a severe earthquake with an instrumental magnitude MI = 6.6 (Mw = 6.5) occurred on the Eastern Anatolian Fault Zone in Sivrice-Elazığ center at 20:55 (local Time). The earthquake was felt in Eastern Anatolia, Southeastern Anatolia, Central Anatolia and Black Sea regions. In the study, it was investigated whether there is any change in the locations of TNPGN-Active stations in the impact area of Sivrice-Elazığ earthquake. In this context, the magnitudes and directions of the movements of ELAZ, ERGN, MALY and SIV1 TNPGN-Active stations were determined. 24-hour data 7 days before and 7 days after the earthquake was evaluated in Online Positioning User Service (OPUS) and Australian Online GPS Processing Service (AUSPOS) web-based data processing services, and daily exact coordinate data sets were obtained. The results of both assessment services gave similar or close results. As a result of the evaluation, the deformations detected at ELAZ, ERGN, MALY and SIV1 TNPGN-Active stations were determined significantly.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2020Genelleştirilmiş regresyon sinir ağı ve bazı enterpolasyon yöntemlerini kullanarak yerel jeoid belirleme: Kars, Türkiye'de bir vaka çalışması
Akar, Alper; Konakoğlu, Berkant
Bu çalışmada Türkiye’nin doğusunda yer alan Kars il sınırları içerisinde bulunan 641 tane GNSS/nivelman noktasına dayalı olarak, genelleştirilmiş regresyon yapay sinir ağı (GRNN), ağırlıklı ortalama (WA), multikuadrik (MQ) fonksiyonu, ters multikuadrik (IMQ) fonksiyonu ve yerel polinom (LP) yöntemleri kullanılarak en uygun yerel jeoid modelinin belirlenmesi amaçlanmıştır. Lokal jeoid belirlemede kullanılan bu yöntemler arasından GRNN yöntemi ile yapılan çalışmaların sayısı literatürde oldukça sınırlıdır. Modelin performansını test etmek için 169 tane GNSS/nivelman noktası test verisi olarak seçilmiştir. Referans noktaları ve test noktaları seçilirken, bu noktaların çalışma alanı içerisinde homojen olarak dağılmasına özen gösterilmiştir. Farklı yöntemlerden elde edilen sonuçların doğruluğunu ve hata oranlarını öğrenmek için, karesel ortalama hata (RMSE), ortalama mutlak hata (MAE) ve belirlilik katsayısı (R2 ) kriterleri kullanılmıştır. Analiz sonuçlarına göre GRNN metodu, diğer interpolasyon yöntemlerine göre daha iyi sonuçlar vermiştir. Bu sonuçlar, GRNN metodunun çeşitli jeodezi problemlerinin modellenmesinde dikkate alınabileceğini göstermiştir..
RDL Kalıcı Kaydıİncele