KKKerim Karadağ

Kerim Karadağ

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Kerim Karadağ has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Comparative Analysis of Geographical Factors Affecting Paddy (Oryza sativa L.) Yields in Türkiye Using Random Forest and ANOVA: The Case of Kırıkkale, Balıkesir, Diyarbakır and Şanlıurfa

    by Mehmet Özcanlı, Kerim Karadağ

    Rice (Oryza sativa L.) is a staple food for nearly half of the global population and a strategic crop for Turkey, where inter-provincial yield disparities remain pronounced. This study aims to classify provincial rice yield levels in Turkey for the 2004–2024 period using TurkStat data and to quantify the relative contribution of 14 environmental, edaphic and agronomic parameters driving these differences. Preliminary analyses identified Kırıkkale (21-year mean 908.3 kg/da) as the high-yield province, Balıkesir (747.7 kg/da) as the medium-yield province, and Diyarbakır (448.1 kg/da) and Şanlıurfa (440.5 kg/da) as the low- and lowest-yield provinces, respectively. A 14-parameter dataset compiled from field measurements and published province-level studies was analysed using Principal Component Analysis (PCA), Random Forest (RF) classification and one-way Analysis of Variance (ANOVA).With a 70/30 train/test split, the RF model achieved 93.47% accuracy, 0.9764 ROC-AUC and a mean variance of 0.0145. Gini-based variable importance ranked soil moisture, organic matter, soil pH, rainfall and temperature as the most influential drivers of yield, and ANOVA confirmed statistically significant differences across yield classes for these variables (all p < 0.001). Findings indicate that low yields in south-eastern Anatolia are largely driven by inadequate soil moisture management, low organic matter content, elevated soil pH and summer heat stress, whereas Kırıkkale’s high yields are associated with more balanced soil–water relations. Results provide evidence-based guidance for region-specific rice production policies and data-driven decision support in Türkiye.

  • Open Access

    Comparative Analysis of Geographical Factors Affecting Paddy (Oryza sativa L.) Yields in Türkiye Using Random Forest and ANOVA: The Case of Kırıkkale, Balıkesir, Diyarbakır and Şanlıurfa

    by Mehmet Özcanlı, Kerim Karadağ

    Rice (Oryza sativa L.) is a staple food for nearly half of the global population and a strategic crop for Turkey, where inter-provincial yield disparities remain pronounced. This study aims to classify provincial rice yield levels in Turkey for the 2004–2024 period using TurkStat data and to quantify the relative contribution of 14 environmental, edaphic and agronomic parameters driving these differences. Preliminary analyses identified Kırıkkale (21-year mean 908.3 kg/da) as the high-yield province, Balıkesir (747.7 kg/da) as the medium-yield province, and Diyarbakır (448.1 kg/da) and Şanlıurfa (440.5 kg/da) as the low- and lowest-yield provinces, respectively. A 14-parameter dataset compiled from field measurements and published province-level studies was analysed using Principal Component Analysis (PCA), Random Forest (RF) classification and one-way Analysis of Variance (ANOVA).With a 70/30 train/test split, the RF model achieved 93.47% accuracy, 0.9764 ROC-AUC and a mean variance of 0.0145. Gini-based variable importance ranked soil moisture, organic matter, soil pH, rainfall and temperature as the most influential drivers of yield, and ANOVA confirmed statistically significant differences across yield classes for these variables (all p < 0.001). Findings indicate that low yields in south-eastern Anatolia are largely driven by inadequate soil moisture management, low organic matter content, elevated soil pH and summer heat stress, whereas Kırıkkale’s high yields are associated with more balanced soil–water relations. Results provide evidence-based guidance for region-specific rice production policies and data-driven decision support in Türkiye.

  • Improving power quality in fuel cell applications and deep learning based analysis

    by Ünal Yilmaz, Kerim Karadağ, Süleyman Bayram Gönüllü

    Power quality issues such as voltage sags, swells, and harmonics that hinder efficient energy transfer in grid-connected systems with sensitive loads lead to grid instability and potential load damage. This study proposes an improved hybrid power architecture that integrates grid and precise load management in a fuel cell system with a maximum power algorithm, performing pulse width modulation (PWM) prediction using an offline-trained deep learning method from dynamic voltage restorer (DVR) data. Grid-injected current and voltage are regulated using proportional–resonant and phase-locked loop (PR-PLL) controllers, while the DVR uses PLL-based synchronization and hysteresis control. Additionally, voltage and switching-signal data are processed with a recurrent neural network (RNN) to enable predictive analysis and estimation of inverter PWM patterns. The proposed data-driven control method aims to reduce the instantaneous processing load and dynamic response times of conventional controllers, thereby achieving high power quality and efficiency in renewable energy integration. The system’s success has been verified by testing it under temperature variations and sudden voltage fluctuations. The DC-link voltage was regulated at 400 V, current harmonic distortion was limited to approximately 5%, a power factor above 0.98 was achieved, and the sensitive load voltage remained at its nominal value despite voltage sags and swells. The mean squared error (MSE) was 0.0251 in the RNN method applied for inverter PWM estimation and analysis.

  • Open Access

    Machine Learning-Based Classification of Soil Parent Materials Using Elemental Concentration and Vis-NIR Data

    by Yüsra İnci, Ali Volkan Bilgili, Recep Gündoğan, Gafur Gözükara, Kerim Karadağ, Mehmet Emin Tenekeci

    In soil science, the allocation of soil samples to their respective origins holds paramount significance, as it serves as a crucial investigative tool. In recent times, with the increasing use of proximal sensing and advancements in machine-learning techniques, new approaches have accompanied these developments, enhancing the effectiveness of soil utilization in soil science. This study investigates soil classification based on four parent materials. For this purpose, a total of 59 soil samples were collected from 12 profiles and the vicinity of each profile at a depth of 0–30 cm. Surface soil samples were analyzed for elemental concentrations using X-Ray fluorescence (XRF) and inductively coupled plasma–optical emission spectrometry (ICP-OES) and soil spectra using a visible near-infrared (Vis-NIR) spectrometer. Soil samples collected from soil profiles (12 soil samples) and surface (47 soil samples) were used to classify parent materials using machine learning-based algorithms such as Support Vector Machine (SVM), Ensemble Subspace k-Near Neighbor (ESKNN), and Ensemble Bagged Trees (EBTs). Additionally, as a validation of the classification techniques, the dataset was subjected to five-fold cross-validation and independent sample set splitting (80% calibration and 20% validation). Evaluation metrics such as accuracy, F score, and G mean were used to evaluate prediction performance. Depending on the dataset and algorithm used, the classification success rates varied between 70% and 100%. Overall, the ESKNN (99%) produced better results than other classification methods. Additionally, Relief algorithms were employed to identify key variables for each dataset (ICP-OES: CaO, Fe2O3, Al2O3, MgO, and MnO; XRF: SiO2, CaO, Fe2O3, Al2O, and MnO; Vis-NIR: 567, 571, 572, 573, and 574 nm). Subsequent soil reclassification using these reduced variables revealed reduced accuracies using Vis-NIR data, with ESKNN still yielding the best results.


  • Open Access

    A Novel Chemometric Learning Of Virgin And Deep Frying Olive-Oil By Fourier Transform Infrared Spectroscopy (FT-IR)

    by Kerim Karadağ, Gizem Yucegonul, Stephen Steve Kelley, Eyyüp Karaoğul

    The aim of this study is to examine the machine learning of chemometrically fried oils in virgin olive oil and eight times used olive oil compared using Fourier Transform Infrared spectroscopy (FT-IR). Deep-Frying Oils (DFO was carried out 8 times for 20 minutes. Because of chemical quality of oils, Cis, Trans, Ester, Methyl, Carbonyl, peroxide, unsatrated peroxide and ether groups were used in These results were evaluated by classification and regression using machine learning methods. For these evaluations, firstly classification and regression were made using all properties of these index. In classification models, Support Vector Machines (SVM), K Closest Neighborhood (KNN), Decision Tree (DT) were used. The evaluation was carried out in two stages. In the first stage, half of the dataset was used for training and the other half for testing. In the second stage, all data data was used for training and testing using cross validation (CV) method. The success results obtained using the all data set were 94% with Support Vector Machines and K Nearest Neighborhood methods. According to chemometric strategy, differences between virgin olive oils and DFO were found by high accurancy in this study. This phenomenon also could be possible for other oil type and degree of purity. Results illustrated that the method is very suitable and exact for detection deteriotion of olive oil.

  • Open Access

    Computer aided decision making to use optimum water in safflower growing

    by Kerim Karadağ

    N plants, it is one of the important factors to provide ecological factors for productivity. Plants perceive the effects of environmental factors outside as stress and create appropriate physiological responses in their metabolism. Water stress is a type of abiotic stress and is one of the important factors affecting the growth and development of plants. Irrigation water management is very important for sustainable use of water resources. Therefore, support tools are becoming increasingly important in deciding irrigation. With the developments the technology, computerized support applications are usually used in agricultural areas. In the study, it is aimed to determine the effects of irrigation applications performed in different periods on yield quality and spectral reflections of safflower plant and to create applicable irrigation programs in safflower cultivation. From the reflections detained from safflower leaves by using spectroradiometer device, the determination of safflower plant according to water ratio different situations is done. Reflections are taken as three groups where the plants are grown at wavelengths of 325 nm to 1075 nm. Water due diligence related with safflower is consist of two stages. The first stage is the provision of the feature vector, the second stage is the classification of the feature vector related to data. As classification methods, support vector machine, k-nearest neighbor and decision tree are used. In comparison of three groups, the average value of the performance is high. As a result, considering the fallowed method and the procedure used, it is evaluated that such studies can be used in agriculture and cultivation.


  • KAN VERMEYE ELVERİŞLİ DONÖRLERİN MAKİNE ÖĞRENME YÖNTEMLERİ İLE TESPİTİ

    by Kerim Karadağ

    İnsanlar hayatları boyunca farklı zamanlarda çeşitli sebeplerden dolayı kan ve kan ürünlerine gerek duymaktadırlar. Kan ve kandan elde edilen ürünler laboratuvar koşullarında elde edilemeyip yalnızca insandan elde edildiğinden, hayati önem taşıyan kanın sağlıklı bireylerden sağlanması gerekmektedir. Karaciğer rahatsızlıkları ile ilgili, Hepatit çeşitleri, karaciğer kanseri, karaciğer büyümesi, karaciğer yetmezliği, siroz ve benzeri hastalıklar kanın durumunu belirleyen etmenlerin başında gelir. Bu hastalıklar ilerledikçe telafisi mümkün olmayan zararlara yol açabileceği için erken teşhis edilip tedavi edilmesi ve kan verilecek kişilere de bulaş riskini ortadan kaldırmak için hayati önem arz etmektedir. Son yıllarda birçok alanda kullanılan makine destekli öğrenme yöntemleri, bu alanda da geleneksel yöntemlere ilaveten hekimlere fikir verici olarak kullanılmaktadır. Bu çalışmada amaç, makine öğrenme yöntemleri ile karaciğer hastalıklarının tespiti ve donörlerin kan bağışı yapmaya elverişli olup olmadıklarını kan değerlerinden tespit etmektir. Sınıflandırma için, Karar Ağaçları, Destek Vektör Makinesi ve k-en yakın komşuluk algoritmaları kullanılıp doğruluk ve gerçek oran performans ölçütleri ile değerlendirilmiştir.