BŞBahadır Şin

Bahadır Şin

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bahadır Şin has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • YOLO-Powered Detection of Commelina communis L. as an Invasive Weed in Tea Gardens of Rize, Türkiye

    by Bahadır Şin, Nur Sivri, Lerzan Öztürk

    Commelina communis L. (Asiatic dayflower) is an invasive weed species that negatively affects crop productivity in many agricultural systems. This weed species is highly prevalent in tea-growing regions of Rize Province. This study aimed to develop and compare the performance of YOLO-based object detection models to automate the identification of C. communis in field imagery and laboratory. Two experimental frameworks were implemented. First, four YOLOv5 variants (n, s, m, l) were trained using the Google Colab platform and evaluated based on performance metrics, including Precision, Recall, and mAP@0.5. Among the models, YOLOv5l demonstrated the best overall performance with a Precision of 0.96, Recall of 0.96, F1 score of 0.96, and mAP@0.5 of 0.97, followed closely by YOLOv5m. YOLOv5n, the smallest and fastest model, showed the lowest detection accuracy. Secondly, three alternative models (YOLO-NAS, YOLOv11 and YOLOv12) were trained on 110 annotated field images via the Roboflow platform. The YOLO-NAS Accurate model outperformed the others with a mAP@0.5 of 96%, a Precision of 91%, and a Recall of 97.0%. YOLOv11 followed closely (mAP@0.5: 97%), while YOLOv12, though the fastest in inference, yielded slightly lower accuracy (mAP@0.5: 92%). Overall, the study demonstrated that all models achieved high performance in the detection of C. communis, with YOLOv5l, YOLOv11, YOLOv12, and YOLO-NAS Accurate producing the most accurate results. These findings confirm that YOLO-based deep learning models can be effectively utilized for very fast, at no cost, and accurate weed detection in agricultural settings, supporting their integration into precision weed management systems.

  • Open Access

    Integrating morphological and deep learning approaches for the identification of economically important nematode genera in vineyards: Mesocriconema and Xiphinema

    by L. Öztürk, B. Şi̇n

    Summary: Accurate identification of plant-parasitic nematodes is fundamental to effective crop protection and the maintenance of soil ecosystem integrity. This study integrates morphological characterization with deep learning-based object detection to enhance diagnostic accuracy for economically important nematode genera, Xiphinema and Mesocriconema , associated with vineyards. Three advanced YOLO architectures [YOLO-NAS, YOLOv11, and Roboflow 3.0 (YOLOv8 architecture)] were trained and evaluated on a high-resolution annotated microscopic image dataset consisting of 961 images and 1.034 bounding-box annotations. Although the target nematode genera display considerable morphological variability and genetic divergence among populations, the present investigation focused on genus-level detection of M. xenoplax and X. pachtaicum . These two major ectoparasitic nematodes cause significant damage to grapevine root systems. Among the models tested, YOLOv11 achieved the highest detection accuracy, with a precision of 95.7 % and an mAP@50 of 93.2 %. YOLO-NAS exhibited comparable performance (mAP@50 = 92.7 %, precision = 93.1 %, recall = 84.9 %), while Roboflow 3.0 (YOLOv8 architecture) yielded satisfactory results (mAP@50 = 89.4 %), indicating its applicability for real-time diagnostic workflows. This integration of taxonomic expertise with deep learning represents a new methodological framework for nematode identification. All models exhibited rapid convergence and stable learning dynamics during training. The findings underscore the potential of YOLO-based frameworks as efficient, scalable, and reproducible tools that complement classical morphological and molecular identification, contributing to precision agriculture and sustainable nematode management strategies.

  • Farklı Bölgelerden Toplanan Verbascum (Sığırkuyruğu) Türlerinin Metanol Ekstraktlarının Rhizoctonia solani’ye Karşı Antifungal Aktivitesi

    by Bahadır Şin, Raziye Koçak, Özden Salman

    Bitkiler, içeriklerindeki sekonder bileşikler sayesinde bitki patojenleriyle mücadelede önemli doğal kaynaklar arasında yer almaktadır. Bu çalışmada, ekolojik olarak farklı lokasyonlardan [Sakarya (Arifiye, Karasu), Konya, Bolu ve Manisa] toplanan Verbascum (Sığırkuyruğu) türlerine ait metanol ekstraktlarının, toprak kökenli ve geniş konukçu aralığına sahip fitopatojen fungus Rhizoctonia solani (J.G. Kühn) üzerindeki antifungal etkileri in vitro koşullarda araştırılmıştır. Verbascum türlerinin çiçek ve yaprak kısımlarından elde edilen metanol ekstraktlarının farklı konsantrasyonları (%0,5; %1; %2 ve %4) besi ortamında miselyal gelişimi inhibe etme potansiyeli değerlendirilmiştir. Tüm ekstraktlar belirli düzeylerde antifungal aktivite göstermiştir. En yüksek inhibisyon Konya örneğinde (%55), ikinci sırada ise Karasu örneğinde (%45) gözlenmiştir. Diğer lokasyonlardan elde edilen ekstraktlar ise %7,5 ile %36,25 arasında değişen inhibisyon değerleri sergilemiştir. Sonuçlar, Verbascum türlerinden elde edilen metanol ekstraktlarının R. solani’ye karşı antifungal aktivite gösterdiğini ve etkinin uygulanan doza bağlı olarak arttığını ortaya koymaktadır. Bulgular, Verbascum türlerinin içerdiği aktif bileşiklerin belirlenmesi ve biyolojik mücadelede alternatif doğal fungisitler olarak kullanılma potansiyellerinin ileri fitokimyasal ve biyolojik araştırmalarla desteklenmesi gerektiğini göstermektedir.


  • Entegre Zararlı Yönetimi Çalışmalarında Akıllı Tarım Sistemlerinin Kullanım Olanakları

    by Ceyda Güler, Bahadır Şin, Salih Karabörklü

    Entegre zararlı yönetimi (EZY),tarımsal üretimdeki zararlı popülasyonlarını ekonomik ve ekolojik açıdan makul seviyelerde tutmayı amaçlayan bir yaklaşımdır. EZY, yalnızca zararlılarla mücadele etmeyi değil; çevre ve insan sağlığını korumayı, doğal düşmanları desteklemeyi ve ekonomik kayıpları minimize etmeyi hedeflemektedir. Günümüzde dijital teknolojilerin hızla gelişimi tarımsal alanlarda zararlı böceklerin hızlı ve doğru şekilde tespit edilmesine olanak tanımıştır. Tarım alanlarında zararlıların erken dönemde tespit edilmesi, popülasyon yoğunluğu artmadan gerekli önlemlerin alınması, uygun mücadele yönteminin belirlenmesi, verim ve kalite kayıplarının önlenmesi açısından büyük önem taşımaktadır. Nesnelerin interneti (IoT), sensörler, dronlar, görüntü işleme teknikleri, yapay zekâ destekli karar destek sistemleri ve otomasyon uygulamaları sayesinde zararlıların erken tespiti, popülasyon dinamiklerinin izlenmesi ve hedefe yönelik mücadeleyi mümkün hale getirmektedir. Bu teknolojiler, makine öğrenmesi ve derin öğrenme algoritmalarıyla birleştirildiğinde, zararlı popülasyonlarının izlenmesi, stres belirtilerinin tanımlanması ve mücadele stratejilerinin optimize edilmesi açısından önemli kazanımlar sağlamaktadır. Görüntü işleme ve sensör tabanlı sistemlerle yapılan çalışmalar, bitkilerde zararlı kaynaklı stresin spektral, termal veya akustik değişimlerle belirlenebildiğini ortaya koymaktadır. Özellikle dron tabanlı görüntüleme sistemleri ve otonom robotlar, geniş tarım alanlarında hızlı veri toplama ve yerinde değerlendirme olanağı sunarak klasik gözlem yöntemlerinin ötesine geçmektedir. Bu yaklaşım, yalnızca zararlı kontrolünde değil; aynı zamanda iklim değişikliğine uyum, kaynak verimliliği ve sürdürülebilir tarım hedeflerinin gerçekleştirilmesinde de stratejik bir öneme sahiptir. Bu durum hem pestisit kullanımının azaltılması hem de çevre dostu ve ekonomik bir üretim sürecinin desteklenmesine katkı sağlayacaktır. Bu çalışma kapsamında, entegre zararlı yönetiminde akıllı tarım sistemlerinin kullanım olanakları ele alınmış ve zararlı böceklere yönelik yapılan araştırmalar derlenmiştir.

  • Evaluation of the Antifungal Effects of Datura stramonium Extracts on Sclerotinia sclerotiorum and Rhizoctonia solani under In Vitro Conditions

    by Raziye Koçak, Özden Salman, Bahadır Şin

    Plant pathogenic fungi pose a serious threat to global agricultural productivity, prompting the search for environmentally friendly alternatives to synthetic fungicides. In this study, the antifungal effects of methanol and ethanol extracts obtained from the aerial green parts of Datura stramonium were investigated under in vitro conditions against the major plant pathogens Sclerotinia sclerotiorum and Rhizoctonia solani. These pathogens cause severe losses in the production and yield of many plant species. Different concentrations (1.0%, 2.0%, and 4.0%) of Datura stramonium extracts were applied to both pathogens, and the obtained data were compared. The results revealed that the methanolic extract exhibited higher antifungal activity compared to the ethanolic extract. Specifically, the methanol extract provided 12% greater inhibition against S. sclerotiorum and 22% greater inhibition against R. solani than the ethanol extract. It was observed that the antifungal effect increased in a dose-dependent manner, and at a 4.0% concentration in both solvents, mycelial growth of S. sclerotiorum and R. solani was completely inhibited. The highest inhibition effect was observed in the 2% concentration of the methanolic extract, where R. solani mycelial growth was suppressed by 77.77%, and S. sclerotiorum by 72.22%. In contrast, the antifungal activity of ethanolic extracts at the same concentration was found to be lower. In conclusion, extracts obtained from the aerial green parts of Datura stramonium have been shown to possess antifungal potential against plant pathogens when dissolved in different solvents. This suggests that they could be evaluated as a natural biofungicide source for controlling phytopathogenic fungi.


  • Open Access

    A comparative applied analysis of six robotic-assisted weeding systems in sugar beets

    by Sonja I. Kimmel, Matthias Schumacher, Michael Spaeth, Markus Sökefeld, Oyebanji O. Alagbo, Alicia Allmendinger, Dionisio Andujar, Therese W. Berge, Reiner Braun, Sergiu Cioca Parasca, et al.

    Effective weed management is crucial in the critical period of sugar beet production, but often lacks sustainability and environmental protection. Recent advancements in sensor-based weed control systems have rendered the latter a realistic prospect, which demands detailed analyses, especially under suboptimal field conditions. The present study analysed six robotic-assisted weed control systems (RAWS) in three experiments on sugar beets in 2024, conducted under dry soil and high weed pressure. The experiments included sensor-based inter-row and intra-row hoeing, spot-and band-spraying and were compared to a broadcast herbicide treatment and an untreated control. Weed control efficacy (WCE) in the intra-and inter-row areas, as well as weed species composition and crop plant damage, were assessed after treatment. The data show that intra-row WCE of two hoeing robots (Farming GT® and Robovator®) equipped with


  • Effectıveness of Drone-Based Herbıcıde Applıcatıons in Sılage Corn Productıon

    by Bahadır Şin

    Drone technology has emerged as a transformative tool in precision agriculture, offering targeted and efficient solutions for herbicide application. This study evaluates the impact of drone-based herbicide spraying on plant growth and yield parameters in silage corn production compared to conventional tractor-based applications. Among the treatments, the 4 L/2 m and 4 L/3 m drone applications resulted in the highest plant heights of 240.5 cm and 258.0 cm, respectively, significantly surpassing the control (194.9 cm) and tractor (196.7 cm) treatments. In terms of cob weight, the 4 L/3 m treatment demonstrated the most substantial increase, whereas the 2 L/2 m treatment yielded the lowest cob weight. The 4 L/2 m treatment also exhibited superior performance in cob length, kernel row number, and total kernel count, recording the highest value of 605.6 kernels per cob. Statistical analyses revealed that higher herbicide dosages applied via drone significantly influenced grain yield and plant growth, with high-dose treatments (4 L/2 m and 4 L/3 m) achieving the greatest impact on key agronomic traits. Total stem weight, a critical factor in silage corn production, was notably enhanced under high-dose applications, with the 4 L/2 m treatment achieving the highest stem weight of 4.234 kg. Similarly, total ear weight followed the same trend, confirming the efficacy of high-dose drone applications. The statistical grouping of treatments indicated that high-dose applications (4 L/3 m and 3 L/3 m) consistently outperformed lower-dose and control treatments across multiple plant parameters. These findings underscore the potential of drone-based herbicide application as a precision-driven alternative to traditional methods, optimizing crop yield while reducing environmental impact and operational costs. The study suggests that drone-based application systems can be effectively implemented in silage corn and potentially adapted for use in various agro-ecological regions.


  • Determination of some biological properties of the seeds of the Johnson grass (Sorghum halepense (L.) Pers.)

    by Bahadır Şin, İzzet Kadıoğlu, Celal Yıldırım

    Dormancy is an important factor affecting seed germination and the emergence of weeds. In this study, the intensity of dormancy in freshly collected seeds of Sorghum halepense (L.) Pers. was determined, and various methods to break this dormancy were evaluated. These methods included sulfuric acid application, sanding, soaking in distilled water, folding method application, and gibberellic acid application. Additionally, the study aimed to determine the optimal, maximum, and minimum germination temperatures and assess seed germination at different burial depths. According to the experimental results, the most effective method for breaking dormancy was the application of 62.5% sulfuric acid for 30 minutes. The ideal germination temperature was found to be 30°C, with a germination rate of 87%. The minimum temperature for germination was 15°C (6% germination), and the maximum temperature was 40°C (48% germination). In terms of sowing depth, the highest germination rate was observed at a depth of 3 cm, where 50% of seeds germinated. It was also noted that the germination rate gradually decreased with increasing burial depth. The results of these experiments provide valuable information on effective methods for breaking seed dormancy in Sorghum halepense and offer insights into the optimal conditions for seed germination.


  • The Effect of Weed Control at Different Periods on Antioxidant Content of Faba Bean (Vicia faba L.)

    by Bahadir Şin, Melike Köse, Mustafa Yılmaz

    Faba bean (Vicia faba L.) is a significant member of the Fabaceae family, known for its high protein content and rich phenolic compounds essential for human nutrition. These phenolic compounds, which belong to the group of secondary metabolites, serve as important dietary components. Secondary metabolites, act as plant defence mechanisms and can fluctuate under stress conditions. Weeds negatively impact the growth of cultivated plants by competing for nutrients and creating a stressful environment. This study evaluated the effects of weeds on the yield and quality parameters of faba bean. Conducted in Sakarya, the research aimed to determine how weed control frequency affects the yield and some secondary metabolites of faba bean. The experiment used a randomized block design with four replications and included four faba bean genotypes: two registered varieties (Eresen-87 and Salkım) and two local populations (Bilecik and Sakarya). Weed control treatments; comprised weedy control, hoeing every 15 days, and hoeing every 30 days. Measured parameters included plant height (cm), number of pods per plant, number of seeds per pod, 1000 seed weight (g), dry seed yield (g), and DPPH radical scavenging activity (%). Data were analyzed using Duncan’s Multiple Range Test with SPSS, revealing statistically significant differences (p<0.05) in all measured parameters. The tallest plants were found in the Salkım×Control plot, while the shortest were in Sakarya×15. The highest number of pods occurred in Sakarya×30, and the lowest in Eresen-87×15. The highest number of seeds per pod was recorded in Bilecik×15, while the lowest was in all treatments of the Salkım variety and the Eresen-87×15 plot. The highest dry seed yield came from Bilecik×15, with the lowest from Eresen-87×30. DPPH activity peaked in Bilecik×Control, indicating significant differences in yield and nutritional content among faba bean genotypes. These findings indicate that different genotypes excel in various agricultural and nutritional characteristics, demonstrating that these differences can play an important role in shaping future production strategies.