Nur Sivri
Research Subjects
Nur Sivri has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Lerzan Öztürk
Faculty of Arts and Sciences, Namık Kemal University, Tekirdağ, Turkey
3 shared publications - Bahadır Şin
Plant Protection Department, Faculty of Agriculture, Sakarya University of Applied Science Sakarya , Türkiye
2 shared publications - Gürkan Güvenç Avcı
Tekirdağ Bağcılık Arşatırma Enstitüsü
1 shared publication - İbrahim Halil Elekcioğlu
Cukurova Universitesi
1 shared publication - İzzet Kadıoğlu
Retired Faculty Member, Anamur
1 shared publication
Latest Publications
- 28 September 2026
- Published by Tekirdag Ziraat Fakultesi Dergisi in Tekirdağ Ziraat Fakültesi Dergisi
- Vol. 23 (4) , 1234-1246
YOLO-Powered Detection of Commelina communis L. as an Invasive Weed in Tea Gardens of Rize, Türkiye
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.
- 28 September 2026
- Published by Tekirdag Ziraat Fakultesi Dergisi in Tekirdağ Ziraat Fakültesi Dergisi
- Vol. 23 (4) , 1234-1246
YOLO-Powered Detection of Commelina communis L. as an Invasive Weed in Tea Gardens of Rize, Türkiye
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
- 5 January 2024
- Published by The Journal of Ege University Faculty of Agriculture in Ege Üniversitesi Ziraat Fakültesi Dergisi
- Vol. 60 (4) , 627-638
Determination of the soil health status of wheat fields in Tekirdağ, Türkiye, based on nematode diversity
Objective: A study was conducted in wheat cultivation areas in Tekirdağ to estimate the soil health of fields using nematode biodiversity indices. Material and Methods: In the study, nematode taxa identified in wheat fields were subjected to community and food web analyses and several indices were calculated to determine the health status of soils in sampled areas. Results and Conclusion Nematodes belonging to 41 genera were identified in wheat fields. The mean values of 10 biodiversity indices calculated in each sampled field were as follows; the Maturity index (MI): 2.26±0.28; the Maturity index MI2-5: 2.32±0.33; the Shannon-Weiner diversity index (H′): 2.03±0.24, the Evennes (J′): 0.90±0.06, the Genera Richness index (GR): 8.32±3.17, the Channel index (CI): 91±20.44; the Basal index (BI): 42.35±12.66; the Enrichment index (EI): 41.93±14.3, the Structure index (SI): 33.6±26.49 and the Plant-parasitic (PPI) index: 2.89±0.17. The nematode faunal indices indicate that 21% of surveyed wheat fields have well-developed and 79% have degraded soil profiles.
- 5 January 2024
- Published by The Journal of Ege University Faculty of Agriculture in Ege Üniversitesi Ziraat Fakültesi Dergisi
- Vol. 60 (4) , 627-638
Open AccessDetermination of the soil health status of wheat fields in Tekirdağ, Türkiye, based on nematode diversity
Objective: A study was conducted in wheat cultivation areas in Tekirdağ to estimate the soil health of fields using nematode biodiversity indices. Material and Methods: In the study, nematode taxa identified in wheat fields were subjected to community and food web analyses and several indices were calculated to determine the health status of soils in sampled areas. Results and Conclusion Nematodes belonging to 41 genera were identified in wheat fields. The mean values of 10 biodiversity indices calculated in each sampled field were as follows; the Maturity index (MI): 2.26±0.28; the Maturity index MI2-5: 2.32±0.33; the Shannon-Weiner diversity index (H′): 2.03±0.24, the Evennes (J′): 0.90±0.06, the Genera Richness index (GR): 8.32±3.17, the Channel index (CI): 91±20.44; the Basal index (BI): 42.35±12.66; the Enrichment index (EI): 41.93±14.3, the Structure index (SI): 33.6±26.49 and the Plant-parasitic (PPI) index: 2.89±0.17. The nematode faunal indices indicate that 21% of surveyed wheat fields have well-developed and 79% have degraded soil profiles.
- Open Access
- 13 December 2019
- Published by Turkish Science and Technology Publishing (TURSTEP) in Turkish Journal of Agriculture - Food Science and Technology
- Vol. 7 (12) , 2252-2258
Weed Flora of Cherry, Walnut, Apple, Almond and Pear Orchards in Northwestern Marmara Region of Turkey
A study covering cherry, walnut, apple, almond and pear orchards in Edirne, Kırklareli and Tekirdağ provinces was carried out in 2015-2018 with the aim of determination of weed flora, weed frequencies and densities. Total of 64 species belonging to 30 families were identified in fruit tree orchards. Among all the families the most members were in Asteraceae 13 species, Poaceae, 11 species, Brassicaceae 5 species and Lamiaceae 3 species families. The dominant weed species were Amaranthus retroflexus L., Polygonum aviculare L., Capsella-bursa pastoris L. (Medik)., Concolvulus arvensis L., Lepidium draba L., Raphanus raphanistrum L., Chenopodium album L., Cichorium intybus L. in Tekirdağ while Datura stramonium L. distribution in Edirne Uzunköprü and Kırklareli was remarkably high. Semi parazitic weed Viscum album and full parasite Cuscuta campestris Yunck were also detected in some orchards. V. album was widespread among pear trees while Cuscuta campestris Yunck was detected only in suckers emerged in apple and cherry orchards. According to density A. retroflexus has received the first order with 76 plant/m2, following C. album with 54 plant/m2, Lactuca serriola with 27 plant/m2, D. stramonium L. with 24 plant/m2, Portulaca oleracea with 21 plant/m2
- 13 December 2019
- Published by Turkish Science and Technology Publishing (TURSTEP) in Turkish Journal of Agriculture - Food Science and Technology
- Vol. 7 (12) , 2252-2258
Open AccessWeed Flora of Cherry, Walnut, Apple, Almond and Pear Orchards in Northwestern Marmara Region of Turkey
A study covering cherry, walnut, apple, almond and pear orchards in Edirne, Kırklareli and Tekirdağ provinces was carried out in 2015-2018 with the aim of determination of weed flora, weed frequencies and densities. Total of 64 species belonging to 30 families were identified in fruit tree orchards. Among all the families the most members were in Asteraceae 13 species, Poaceae, 11 species, Brassicaceae 5 species and Lamiaceae 3 species families. The dominant weed species were Amaranthus retroflexus L., Polygonum aviculare L., Capsella-bursa pastoris L. (Medik)., Concolvulus arvensis L., Lepidium draba L., Raphanus raphanistrum L., Chenopodium album L., Cichorium intybus L. in Tekirdağ while Datura stramonium L. distribution in Edirne Uzunköprü and Kırklareli was remarkably high. Semi parazitic weed Viscum album and full parasite Cuscuta campestris Yunck were also detected in some orchards. V. album was widespread among pear trees while Cuscuta campestris Yunck was detected only in suckers emerged in apple and cherry orchards. According to density A. retroflexus has received the first order with 76 plant/m2, following C. album with 54 plant/m2, Lactuca serriola with 27 plant/m2, D. stramonium L. with 24 plant/m2, Portulaca oleracea with 21 plant/m2