Onur Kaplan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Onur Kaplan has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Gordana Kaplan
Eskisehir Technical University
6 shared publications - Resul Comert
Institute of Earth and Space Sciences, Eskisehir Technical University, Eskisehir 26555, Turkey
3 shared publications - Uğur Avdan
Institute of Earth and Space Sciences, Eskisehir Technical University, Eskişehir, Turkey
2 shared publications Ahmet Topcu
Eskisehir Osmangazi University
1 shared publication- Ali Ekber Sever
Civil Engineering Department, Technology Faculty, Isparta University of Applied Sciences, Isparta 32040, Türkiye
1 shared publication - Alper Çabuk
Eskisehir Technical University
1 shared publication
Latest Publications
- Open Access
- 15 October 2026
- Published by Springer Nature
- p. 1308-1314
Nature-Based Intelligence (NBI) for Climate-Resilient Urban Infrastructure: A GeoAI Decision-Support Engine
- 15 October 2026
- Published by Springer Nature
- p. 1308-1314
Open AccessNature-Based Intelligence (NBI) for Climate-Resilient Urban Infrastructure: A GeoAI Decision-Support Engine
- Open Access
- 26 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (19) , 9586
Machine-Learning-Aided First Natural Frequency Estimation for Masonry Building Archetypes
Masonry buildings represent a significant portion of the existing building stock and are particularly vulnerable to seismic actions, making their reliable dynamic characterization essential for seismic assessment, risk mitigation, and retrofit prioritization. Among their global dynamic properties, the first natural frequency is especially relevant, as it reflects the combined influence of geometry, stiffness, mass distribution, material properties, and boundary conditions. However, its estimation often requires experimental testing or detailed numerical modeling, which may not be practical for preliminary or large-scale applications. This study presents a data-driven framework for predicting the first natural frequency of linear-elastic, fixed-base unreinforced masonry (URM) building archetypes using finite element modeling, machine learning algorithms, and regression-based formula development. A parametric database composed of 147 masonry structural models was generated in Abaqus, considering plan width, plan length, structural height, modulus of elasticity, and wall density as input variables. Modal analyses were performed to obtain the corresponding frequency values, which were then used to train and evaluate random forest (RF), XGBoost, LightGBM, CatBoost, and multilayer perceptron models. Because several numerical realizations shared the same underlying geometry, model performance was assessed using group-based nested five-fold cross-validation, with Group-K-Fold applied in both the inner hyperparameter-optimization loop and the outer performance-evaluation loop. Linear and symbolic regression were also implemented to derive explicit equations for practical use. The main contributions of the study are the development of a parametric FE-based database for URM frequency prediction, the use of geometry-grouped nested cross-validation to assess generalization to unseen configurations, and the derivation of explicit regression-based equations as interpretable alternatives to black-box machine-learning models. The multilayer perceptron achieved the best predictive performance for previously unseen geometry groups within the adopted FE-generated database, with an average outer-test of , MAE of Hz, and RMSE of Hz, followed by CatBoost. In addition, symbolic regression provided an explicit nonlinear equation with a favorable balance between prediction accuracy and interpretability. The reported performance therefore reflects prediction within the considered numerical archetype space and should not be interpreted as independent validation against real masonry buildings.- 26 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (19) , 9586
Open AccessMachine-Learning-Aided First Natural Frequency Estimation for Masonry Building Archetypes
Masonry buildings represent a significant portion of the existing building stock and are particularly vulnerable to seismic actions, making their reliable dynamic characterization essential for seismic assessment, risk mitigation, and retrofit prioritization. Among their global dynamic properties, the first natural frequency is especially relevant, as it reflects the combined influence of geometry, stiffness, mass distribution, material properties, and boundary conditions. However, its estimation often requires experimental testing or detailed numerical modeling, which may not be practical for preliminary or large-scale applications. This study presents a data-driven framework for predicting the first natural frequency of linear-elastic, fixed-base unreinforced masonry (URM) building archetypes using finite element modeling, machine learning algorithms, and regression-based formula development. A parametric database composed of 147 masonry structural models was generated in Abaqus, considering plan width, plan length, structural height, modulus of elasticity, and wall density as input variables. Modal analyses were performed to obtain the corresponding frequency values, which were then used to train and evaluate random forest (RF), XGBoost, LightGBM, CatBoost, and multilayer perceptron models. Because several numerical realizations shared the same underlying geometry, model performance was assessed using group-based nested five-fold cross-validation, with Group-K-Fold applied in both the inner hyperparameter-optimization loop and the outer performance-evaluation loop. Linear and symbolic regression were also implemented to derive explicit equations for practical use. The main contributions of the study are the development of a parametric FE-based database for URM frequency prediction, the use of geometry-grouped nested cross-validation to assess generalization to unseen configurations, and the derivation of explicit regression-based equations as interpretable alternatives to black-box machine-learning models. The multilayer perceptron achieved the best predictive performance for previously unseen geometry groups within the adopted FE-generated database, with an average outer-test of , MAE of Hz, and RMSE of Hz, followed by CatBoost. In addition, symbolic regression provided an explicit nonlinear equation with a favorable balance between prediction accuracy and interpretability. The reported performance therefore reflects prediction within the considered numerical archetype space and should not be interpreted as independent validation against real masonry buildings. - Open Access
- 31 March 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (7) , 6067
Machine Learning-Based Classification of Asbestos-Containing Roofs Using Airborne RGB and Thermal Imagery
Detecting asbestos-containing roofs has been of great interest in the past few years as the substance negatively affects human health and the environment. Different remote sensing data have been successfully used for this purpose. However, RGB and thermal data have yet to be investigated. This study aims to investigate the classification of asbestos-containing roofs using RGB and airborne thermal data and state-of-the-art machine learning (ML) classification techniques. With the rapid development of ML reflected in this study, we evaluate three classifiers: Random Forest (RF), Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGBoost). We have used several image enhancement techniques to produce additional bands to improve the classification results. For feature selection, we used the Boruta technique; based on the results, we have constructed four different variations of the dataset. The results showed that the most important features for asbestos-containing roof detection were the investigated spectral indices in this study. From a ML point of view, SVM outperformed RF and XGBoost in the dataset using only the spectral indices, with a balanced accuracy of 0.93. Our results showed that RGB bands could produce as accurate results as the multispectral and hyperspectral data with the addition of spectral indices.
- 31 March 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (7) , 6067
Open AccessMachine Learning-Based Classification of Asbestos-Containing Roofs Using Airborne RGB and Thermal Imagery
Detecting asbestos-containing roofs has been of great interest in the past few years as the substance negatively affects human health and the environment. Different remote sensing data have been successfully used for this purpose. However, RGB and thermal data have yet to be investigated. This study aims to investigate the classification of asbestos-containing roofs using RGB and airborne thermal data and state-of-the-art machine learning (ML) classification techniques. With the rapid development of ML reflected in this study, we evaluate three classifiers: Random Forest (RF), Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGBoost). We have used several image enhancement techniques to produce additional bands to improve the classification results. For feature selection, we used the Boruta technique; based on the results, we have constructed four different variations of the dataset. The results showed that the most important features for asbestos-containing roof detection were the investigated spectral indices in this study. From a ML point of view, SVM outperformed RF and XGBoost in the dataset using only the spectral indices, with a balanced accuracy of 0.93. Our results showed that RGB bands could produce as accurate results as the multispectral and hyperspectral data with the addition of spectral indices.
- Open Access
Amplification in Mechanical Properties of a Lead Rubber Bearing for Various Exposure Times to Low Temperature
In this paper, new formulations to predict the change in mechanical properties, namely, post-yield stiffness and characteristic strength of lead rubber bearings (LRBs) at low ambient temperatures, are proposed based on test results. Proposed formulations consider not only the effect of low temperature but also the effect of exposure time to low temperature. Accordingly, a full-scale LRB was tested dynamically after being conditioned at temperatures of −20, −10, 0, and 20 °C for 3, 6, and 24 h. During the displacement-controlled cyclic tests, various levels of shear strain were applied to the isolator with loading frequencies of 0.1 Hz and 0.5 Hz. Then, force-displacement curves of LRB were recorded, and the corresponding amplifications in its hysteretic properties were noted. The accuracy of existing equations to estimate the amount of amplification in mechanical properties was evaluated through the experimental results. It was found that the existing formulas do not represent the effect of exposure time on LRB characteristics at low temperatures. On the other hand, the proposed equations result in highly accurate estimations of post-yield stiffness and characteristic strength of LRB at low temperatures for different exposure times.
Open AccessAmplification in Mechanical Properties of a Lead Rubber Bearing for Various Exposure Times to Low Temperature
In this paper, new formulations to predict the change in mechanical properties, namely, post-yield stiffness and characteristic strength of lead rubber bearings (LRBs) at low ambient temperatures, are proposed based on test results. Proposed formulations consider not only the effect of low temperature but also the effect of exposure time to low temperature. Accordingly, a full-scale LRB was tested dynamically after being conditioned at temperatures of −20, −10, 0, and 20 °C for 3, 6, and 24 h. During the displacement-controlled cyclic tests, various levels of shear strain were applied to the isolator with loading frequencies of 0.1 Hz and 0.5 Hz. Then, force-displacement curves of LRB were recorded, and the corresponding amplifications in its hysteretic properties were noted. The accuracy of existing equations to estimate the amount of amplification in mechanical properties was evaluated through the experimental results. It was found that the existing formulas do not represent the effect of exposure time on LRB characteristics at low temperatures. On the other hand, the proposed equations result in highly accurate estimations of post-yield stiffness and characteristic strength of LRB at low temperatures for different exposure times.
- Open Access
- 15 October 2022
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 11 (10) , 517
Using Machine Learning to Extract Building Inventory Information Based on LiDAR Data
The extraction of building inventory information is vital for damage assessment and planning and modelling studies. In the last few years, the conventional data extraction for building inventory was overcome using various remote sensing data and techniques. The main objectives of this study were to supply the necessary data for the structural engineers to calculate the seismic performance of existing structures. Thus, we investigated light detection and ranging (LiDAR) derivatives data to classify buildings and extract building inventory information, such as different heights of the buildings and footprint area. The most important data to achieve this was also investigated and classified using machine learning methods, such as Random Forest, Random Tree, and Optimized Forest, over the object-based segmentation results. All of the machine learning methods successfully classified the buildings with high accuracy, whereas the other methods outperformed RT. The height and footprint area results show that the archived sensitivity of the building inventory information is sufficient for the data to be further used in different applications, such as detailed structural health monitoring. Overall, this study presents a methodology that can accurately extract building information. In light of the results, future studies can be directed for investigations on determining the construction year using remote sensing data, such as multi-temporal satellite imagery.
- 15 October 2022
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 11 (10) , 517
Open AccessUsing Machine Learning to Extract Building Inventory Information Based on LiDAR Data
The extraction of building inventory information is vital for damage assessment and planning and modelling studies. In the last few years, the conventional data extraction for building inventory was overcome using various remote sensing data and techniques. The main objectives of this study were to supply the necessary data for the structural engineers to calculate the seismic performance of existing structures. Thus, we investigated light detection and ranging (LiDAR) derivatives data to classify buildings and extract building inventory information, such as different heights of the buildings and footprint area. The most important data to achieve this was also investigated and classified using machine learning methods, such as Random Forest, Random Tree, and Optimized Forest, over the object-based segmentation results. All of the machine learning methods successfully classified the buildings with high accuracy, whereas the other methods outperformed RT. The height and footprint area results show that the archived sensitivity of the building inventory information is sufficient for the data to be further used in different applications, such as detailed structural health monitoring. Overall, this study presents a methodology that can accurately extract building information. In light of the results, future studies can be directed for investigations on determining the construction year using remote sensing data, such as multi-temporal satellite imagery.
- Open Access
Response Spectra-Based Post-Earthquake Rapid Structural Damage Estimation Approach Aided with Remote Sensing Data: 2020 Samos Earthquake
Effective post-event emergency management contributes substantially to communities’ earthquake resilience, and one of the most crucial actions following an earthquake is building damage assessment. On-site inspections are dangerous, expensive, and time-consuming. Remote sensing techniques have shown great potential in localizing the most damaged regions and thus guiding aid and rescue operations in recent earthquakes. Furthermore, to prevent post-earthquake casualties, heavily damaged, unsafe buildings must be identified immediately since in most earthquakes, strong aftershocks can cause such buildings to collapse. The potential of the response spectrum concept for being associated with satellite-based remote sensing data for post-earthquake structural damage estimation was investigated in this study. In this respect, a response spectra-based post-earthquake structural damage estimation method aided by satellite-based remote sensing data was proposed to classify the buildings after an earthquake by prioritizing them based on their expected damage levels, in order to speed up the damage assessment process of critical buildings that can cause casualties in a possible strong aftershock. A case study application was implemented in the Bayrakli region in Izmir, Turkey, the most affected area by the Samos earthquake, on 30 October 2020. The damage estimations made in this research were compared with the in situ damage assessment reports prepared by the Republic of Turkey Ministry of Environment and Urbanization experts. According to the accuracy assessment results, the sensitivity of the method is high (91%), and the necessary time spent by the in situ damage assessment teams to detect the critical buildings would have been significantly reduced for the study area.
Open AccessResponse Spectra-Based Post-Earthquake Rapid Structural Damage Estimation Approach Aided with Remote Sensing Data: 2020 Samos Earthquake
Effective post-event emergency management contributes substantially to communities’ earthquake resilience, and one of the most crucial actions following an earthquake is building damage assessment. On-site inspections are dangerous, expensive, and time-consuming. Remote sensing techniques have shown great potential in localizing the most damaged regions and thus guiding aid and rescue operations in recent earthquakes. Furthermore, to prevent post-earthquake casualties, heavily damaged, unsafe buildings must be identified immediately since in most earthquakes, strong aftershocks can cause such buildings to collapse. The potential of the response spectrum concept for being associated with satellite-based remote sensing data for post-earthquake structural damage estimation was investigated in this study. In this respect, a response spectra-based post-earthquake structural damage estimation method aided by satellite-based remote sensing data was proposed to classify the buildings after an earthquake by prioritizing them based on their expected damage levels, in order to speed up the damage assessment process of critical buildings that can cause casualties in a possible strong aftershock. A case study application was implemented in the Bayrakli region in Izmir, Turkey, the most affected area by the Samos earthquake, on 30 October 2020. The damage estimations made in this research were compared with the in situ damage assessment reports prepared by the Republic of Turkey Ministry of Environment and Urbanization experts. According to the accuracy assessment results, the sensitivity of the method is high (91%), and the necessary time spent by the in situ damage assessment teams to detect the critical buildings would have been significantly reduced for the study area.
- Open Access
- 23 November 2020
- Published by MDPI AG in Environmental Sciences Proceedings
- Vol. 5 (1) , 19
PlanetScope Imagery for Extracting Building Inventory Information
In order to prevent serious damages from a possible earthquake and to determine the possible losses, in settlements under earthquake risk, it is very important to extract building inventory information for further determination of the performance of existing buildings. As conventional methods, such as field investigations, can be time-consuming and costly on an urban scale, approaches that are able to speed up these processes and reduce the costs are required. Determining at least some of the data required to determine the seismic performance of an existing building using alternative methods instead of conventional methods will provide a significant advantage. The study aims to investigate the potential of PlanetScope satellite imagery for extracting building inventory information. Thus, the main objectives of the study are to extract buildings using deep learning methods and to determine the height and the construction period of the buildings. For this purpose, two 3 m PlanetScope satellite images were used over the study area located in Eskisehir, Turkey. Over 30 buildings were located in the study area. The results showed that with PlanetScope Imagery detached buildings can be detected with high accuracy using deep learning methods, their heights can be calculated and the construction period can be determined. For future studies, the obtained information is planned to further be processed in a geographical information system (GIS) for building inventory and to be used for seismic vulnerability assessment studies of existing buildings.
- 23 November 2020
- Published by MDPI AG in Environmental Sciences Proceedings
- Vol. 5 (1) , 19
Open AccessPlanetScope Imagery for Extracting Building Inventory Information
In order to prevent serious damages from a possible earthquake and to determine the possible losses, in settlements under earthquake risk, it is very important to extract building inventory information for further determination of the performance of existing buildings. As conventional methods, such as field investigations, can be time-consuming and costly on an urban scale, approaches that are able to speed up these processes and reduce the costs are required. Determining at least some of the data required to determine the seismic performance of an existing building using alternative methods instead of conventional methods will provide a significant advantage. The study aims to investigate the potential of PlanetScope satellite imagery for extracting building inventory information. Thus, the main objectives of the study are to extract buildings using deep learning methods and to determine the height and the construction period of the buildings. For this purpose, two 3 m PlanetScope satellite images were used over the study area located in Eskisehir, Turkey. Over 30 buildings were located in the study area. The results showed that with PlanetScope Imagery detached buildings can be detected with high accuracy using deep learning methods, their heights can be calculated and the construction period can be determined. For future studies, the obtained information is planned to further be processed in a geographical information system (GIS) for building inventory and to be used for seismic vulnerability assessment studies of existing buildings.
- Open Access
- 31 December 2018
- Published by Anadolu University Journal of Science and Technology – B Theoretical Sciences in Anadolu Üniversitesi Bilim Ve Teknoloji Dergisi - B Teorik Bilimler
- Vol. 6, 192-203
DYNAMIC BEHAVIOR CHANGE OF KÜTAHYA YEŞİL MINARET WITH COVERED AND OPEN BALCONY ARCHITECTURE
There are many Ottoman minarets with different architectural and structural features in Anatolia. But, examples of minarets with covered balcony are very rare. Therefore, in order to protect these minarets against possible earthquakes, it is necessary to investigate the structural properties and determine the dynamic characteristics before performing seismic analysis. In the scope of this paper, the dynamic characteristics of the covered balcony minaret of Green Mosque, which is located in Kütahya were examined. The study includes general information about the structural characteristics of the minaret and the dynamic behavior changes between the cases, which the minaret has open or covered balcony. The determination of the dynamic characteristics of historical minarets is troublesome. Because, the historical masonry minarets have complex stiffness, high heterogeneity and shadowy boundary conditions as observed. Thus, ambient vibration test was performed with aim of defining modal parameters of the minaret. The test was applied using two different types of accelerometers and the results were compared with each other. Since the dynamic behavior of the minaret were also represented with numerical model, solid model were implemented by using the finite element technique. Model updating was performed in order to match the natural frequencies arising from the experimental investigation with those from numerical results. Then, the minaret was modeled as open balcony with the same material properties and geometric dimensions and modal analysis was performed on this new model. The mode shapes and modal frequencies obtained from both models are compared with each other. Whereby, the effect of covered and open balcony to the dynamic behavior of the minaret was interpreted. Furthermore, considering elastic acceleration spectra, calculated horizontal load of the minarets were compared with each other according to the first and second modes.
- 31 December 2018
- Published by Anadolu University Journal of Science and Technology – B Theoretical Sciences in Anadolu Üniversitesi Bilim Ve Teknoloji Dergisi - B Teorik Bilimler
- Vol. 6, 192-203
Open AccessDYNAMIC BEHAVIOR CHANGE OF KÜTAHYA YEŞİL MINARET WITH COVERED AND OPEN BALCONY ARCHITECTURE
There are many Ottoman minarets with different architectural and structural features in Anatolia. But, examples of minarets with covered balcony are very rare. Therefore, in order to protect these minarets against possible earthquakes, it is necessary to investigate the structural properties and determine the dynamic characteristics before performing seismic analysis. In the scope of this paper, the dynamic characteristics of the covered balcony minaret of Green Mosque, which is located in Kütahya were examined. The study includes general information about the structural characteristics of the minaret and the dynamic behavior changes between the cases, which the minaret has open or covered balcony. The determination of the dynamic characteristics of historical minarets is troublesome. Because, the historical masonry minarets have complex stiffness, high heterogeneity and shadowy boundary conditions as observed. Thus, ambient vibration test was performed with aim of defining modal parameters of the minaret. The test was applied using two different types of accelerometers and the results were compared with each other. Since the dynamic behavior of the minaret were also represented with numerical model, solid model were implemented by using the finite element technique. Model updating was performed in order to match the natural frequencies arising from the experimental investigation with those from numerical results. Then, the minaret was modeled as open balcony with the same material properties and geometric dimensions and modal analysis was performed on this new model. The mode shapes and modal frequencies obtained from both models are compared with each other. Whereby, the effect of covered and open balcony to the dynamic behavior of the minaret was interpreted. Furthermore, considering elastic acceleration spectra, calculated horizontal load of the minarets were compared with each other according to the first and second modes.
- 1 June 2018
- Published by International Journal of Engineering and Geoscience in International Journal of Engineering and Geosciences
- Vol. 3 (2) , 56-60
Determination of building materials with IR-Thermography in historical buildings
Lately, IR thermography is frequently applied for important purposes in monitoring buildings such as energy leaking, ventilating and air-conditioning installations, electrical and mechanical installations, moisture detection etc. Nondestructive monitoring methods are essential in case of monitoring historical buildings. It is curtail not to destruct any part of the buildings, which are historically important. Therefore, nondestructive methods need to be used while monitoring this kind of buildings. In this study, IR-Thermography was used in order to distinguish different construction materials that were used to build the walls of a historical building. The thermal monitoring was made with Optris PI-450 long wave infrared camera. The results showed that IR monitoring can be useful to distinguish the building materials without destroying the investigated buildings' plaster or facing. It is observed that the best results can be achieved on higher temperatures at IR-Thermography.
- 1 June 2018
- Published by International Journal of Engineering and Geoscience in International Journal of Engineering and Geosciences
- Vol. 3 (2) , 56-60
Determination of building materials with IR-Thermography in historical buildings
Lately, IR thermography is frequently applied for important purposes in monitoring buildings such as energy leaking, ventilating and air-conditioning installations, electrical and mechanical installations, moisture detection etc. Nondestructive monitoring methods are essential in case of monitoring historical buildings. It is curtail not to destruct any part of the buildings, which are historically important. Therefore, nondestructive methods need to be used while monitoring this kind of buildings. In this study, IR-Thermography was used in order to distinguish different construction materials that were used to build the walls of a historical building. The thermal monitoring was made with Optris PI-450 long wave infrared camera. The results showed that IR monitoring can be useful to distinguish the building materials without destroying the investigated buildings' plaster or facing. It is observed that the best results can be achieved on higher temperatures at IR-Thermography.