Dergiler / Tekirdağ Ziraat Fakültesi Dergisi / 2026 / Cilt: 23 Sayı: 4

Türkiye'nin Rize İli Çay Bahçelerinde Yaygın Bir Yabancı Ot Olarak Commelina communis L.’nin YOLO Tabanlı Tespiti

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

Bahadır Şin(SAKARYA UYGULAMALI BİLİMLER ÜNİVERSİTESİ, UYGULAMALI BİLİMLER FAKÜLTESİ)0000-0002-0109-3662
Nur Sivri(Derepazarı İlçe Tarım ve Orman Müdürlüğü)0000-0003-3621-6121
Sayfa
1234–1246
Yayın Tarihi
2026-09-28
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Genel olarak, bu çalışma tüm modellerin C. communis tespiti açısından yüksek performans sergilediğini ortaya koymuştur.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Commelina communis L. (Asya gün çiçeği), birçok tarımsal üretim sisteminde verimliliği olumsuz etkileyen istilacı bir yabancı ot türüdür.
📊
Temel Bulgular & Veri:Bu kapsamda iki farklı deneysel yaklaşım uygulanmıştır.
💡
Sonuç & Katkı:Genel olarak, bu çalışma tüm modellerin C. communis tespiti açısından yüksek performans sergilediğini ortaya koymuştur.
🔬Tür:Deneysel Tarla Denemesi
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:Görüntü işleme · Yapay zekâ · Tarla ve laboratuvar görüntüleri

Özet

Commelina communis L. (Asya gün çiçeği), birçok tarımsal üretim sisteminde verimliliği olumsuz etkileyen istilacı bir yabancı ot türüdür. Bu yabancı ot, Rize ili çay üretim alanlarında oldukça yaygın olarak bulunmaktadır. Bu çalışmanın amacı, C. communis’in tarla ve laboratuvar görüntülerinde otomatik olarak tanınmasını sağlamak üzere YOLO tabanlı nesne tespiti modellerinin geliştirilmesi ve performanslarının karşılaştırılmasıdır. Bu kapsamda iki farklı deneysel yaklaşım uygulanmıştır. İlk olarak, Google Colab platformu kullanılarak YOLOv5’in dört farklı varyantı (n, s, m, l) eğitilmiş ve Precision, Recall ve [email protected] gibi performans ölçütleri ile değerlendirilmiştir. Bu modeller arasında YOLOv5l, %96 doğruluk, %96 duyarlılık, %96 F1 skoru ve %97 [email protected] değeri ile en yüksek genel performansı göstermiştir. Onu yakından YOLOv5m takip etmiştir. En küçük ve en hızlı model olan YOLOv5n ise en düşük tespit doğruluğunu sergilemiştir. İkinci olarak, Roboflow platformu üzerinden 110 etiketlenmiş tarla görüntüsü kullanılarak üç alternatif model (YOLO-NAS, YOLOv11 ve YOLOv12) eğitilmiştir. Bu modeller arasında YOLO-NAS Accurate modeli, %96 [email protected], %91 kesinlik ve %97 duyarlılık değerleriyle en iyi sonuçları vermiştir. YOLOv11 modeli %97 [email protected] değeri ile onu yakından takip etmiş, en hızlı çıkarım süresine sahip olan YOLOv12 ise %92 [email protected] ile biraz daha düşük bir doğruluk göstermiştir. Genel olarak, bu çalışma tüm modellerin C. communis tespiti açısından yüksek performans sergilediğini ortaya koymuştur. YOLOv5l, YOLOv11, YOLOv12 ve YOLO-NAS Accurate modelleri en doğru sonuçları sağlayan modeller olmuştur. Elde edilen bulgular, YOLO tabanlı derin öğrenme modellerinin tarımsal alanlarda istilacı yabancı otların hızlı, masrafsız ve doğru bir şekilde tespiti için etkili bir şekilde kullanılabileceğini ve hassas yabancı ot yönetim sistemlerine entegre edilebileceğini doğrulamaktadır.

Abstract

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 [email protected]. 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 [email protected] 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 [email protected] of 96%, a Precision of 91%, and a Recall of 97.0%. YOLOv11 followed closely ([email protected]: 97%), while YOLOv12, though the fastest in inference, yielded slightly lower accuracy ([email protected]: 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.

🔖

Bu Makaleye Atıf Yap

Şin, B., Sivri, N., Öztürk, L. (2026). Türkiye'nin Rize İli Çay Bahçelerinde Yaygın Bir Yabancı Ot Olarak Commelina communis L.’nin YOLO Tabanlı Tespiti. Tekirdağ Ziraat Fakültesi Dergisi, Cilt: 23 Sayı: 4, 1234–1246. https://doi.org/10.33462/jotaf.1754783

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (50)

  1. Abid, M. S. Z., Jahan, B., Al Mamun, A., Hossen, M. J. and Mazumder, S.H. (2024). Bangladeshi crops leaf disease detection using YOLOv8. Heliyon, 10: e36694. https://doi.org/10.1016/j.heliyon.2024.e36694
  2. Aldakheel, E. A., Zakariah, M. and Alabdalall, A. H. (2024). Detection and identification of plant leaf diseases using YOLOv4. Frontiers in Plant Science, 15: 1355941. https://doi.org/10.3389/fpls.2024.1355941
  3. Baker, C. A. and Zettler, F. W. (1988). Viruses infecting wild and cultivated species of Commelinaceae. Plant Disease, 72: 513-518. https://doi.org/10.1094/PD-72-0513
  4. Chen, J., Wang, H., Zhang, H., Luo, T., Wei, D., Long, T. and Wang, Z. (2022). Weed detection in sesame fields using a YOLO model with an enhanced attention mechanism and feature fusion. Computers and Electronics in Agriculture, 202: 1-12. https://doi.org/10.1016/j.compag.2022.107412
  5. Deyuan, H. and Defillipps, R. A. (2000). Commelina communis. In: Flora of China 24. Ed(s): Wu, Z. Y., Raven, P. H. and Hong, D. Y., Beijing Science Press, St. Louis Missouri Botanical Garden Press, p. 36, ISBN 962-209-437-6.
  6. Dolatabadian, A., Neik, T. X., Danilevicz, M. F., Upadhyaya, S. R., Batley, J. and Edwards, D. (2025). Image‐based crop disease detection using machine learning. Plant Pathology, 74(1):18-38. https://doi.org/10.1111/ppa.14006
  7. Gang, S., Zhang, S., Zhang, S., Sun, J. and Yang, C. (2023). Broad bean wilt virus 2 in Commelina communis L. in China. Bangladesh Journal of Botany, 52(20): 569–574. https://doi.org/10.3329/bjb.v52i20.68222
  8. Gangadharan, D., Immidichetty, S., Gandhamueni, S., Mupparaju, Y., Gottipati, S. and Simon, U. (2025). Precision weed detection using YOLOv11 for enhanced agriculture management. International Journal of Agriculture Extension and Social Development, 8: 659-666. https://doi.org/10.33545/26180723.2025.v8.i5i.1965
  9. Garcia-Navarrete, O. L., Santamaria, O., Martín-Ramos, P., Valenzuela-Mahecha, M. A. and Navas-Gracia, L. M. (2024). Development of a detection system for types of weeds in maize (Zea mays L.) under greenhouse conditions using the YOLOv5 v7.0 Model. Agriculture, 14(286): 2-13. https://doi.org/10.3390/agriculture14020286
  10. Gibbs, H. A. (2002). A monocot plant identified as an alternate host of the causal agent of bacterial spot of tomato and pepper. HortScience, 37(6): 969-972. https://www.doi.org/10.21273/HORTSCI.37.6.969
  11. Govaerts, R. and Faden, R. B. (2012). World checklist of Commelinaceae. Royal Botanic Gardens, Richmond, U. K. Guo, C., Zheng, S., Cheng, G., Zhang, Y. and Ding, J. (2023). An improved YOLOv4 used for grape detection in unstructured environment. Frontiers in Plant Science, 14: 1209910. https://doi.org/10.3389/fpls.2023.1209910
  12. Guzel, M., Turan, B., Kadioglu, I., Basturk, A., Sin, B. and Sadeghpour, A. (2024). Deep learning for image-based detection of weeds from emergence to maturity in wheat fields. Smart Agricultural Technology, 9, 100552. https://doi.org/10.1016/j.atech.2024.100552
  13. Hartbauer, M. (2024). Artificial neuronal networks are revolutionizing entomological research. Journal of Applied Entomology, 148(2): 232-251. https://doi.org/10.1111/jen.13227
  14. Holm, L. G., Plucknett, D. L., Pancho, J. V. and Herberger, J. P. (1977). The world's worst weeds. Distribution and biology. University Press of Hawaii. 610 pp., Honolulu, Hawaii, U. S. A.
  15. Huang, J., Xia, X., Diao, Z., Li, X., Zhao, S., Zhang, J., Zhang, B. and Li, G. (2024). A lightweight model for weed detection based on the ımproved YOLOv8s network in maize fields. Agronomy, 14(12): 3062. https://doi.org/10.3390/agronomy14123062
  16. IPAU (2025). Asiatic Dayflower (Commelina communis L.). Invasive Plant Atlas of the United States, University of Georgia – Center for Invasive Species and Ecosystem Health. www.invasiveplantatlas.org/subject.cfm?sub=5365 (Accessed Date: 8 July 2025).
  17. Isaac, W.-A., Gao, Z. and Li, M. (2013). Managing Commelina Species: Prospects and Limitations. InTech. https://doi.org/10.5772/55842
  18. Javaid, M., Haleem, A., Khan, I. H. and Suman, R. (2023). Understanding the potential applications of artificial intelligence in agriculture sector. Advanced Agrochem, 2(1): 15-30. https://doi.org/10.1016/j.aac.2022.10.001
  19. Karim, M. J., Nahiduzzaman, M., Ahsan, M. and Haider, J. (2024). Development of an early detection and automatic targeting system for cotton weeds using an improved lightweight YOLOv8 architecture on an edge device. Knowledge Based Systems, 300: 112204. https://doi.org/10.1016/j.knosys.2024.112204
  20. Kew Royal Botanic Gardens. (2025). Herbarium specimen (Barcode No. K001131971). Kew Herbarium (K). https://powo.science.kew.org/taxon/urn:lsid:ipni.org:names:319150-2 (Accessed Date: 8 March 2025).
  21. Kucharek, T. A., Purcifull, D. E., Christie, R. G. and Perkins, K. D. (1998). The association of severe epidemics of cucumber mosaic in commercial fields of pepper and tobacco in North Florida with inoculum in Commelina benghalensis and C. communis. Plant Disease, 82(10): 1172. https://doi.org/10.1094/PDIS.1998.82.10.1172A
  22. Kutbay, H. G. and Uçkan, F. (1998). Phenotypic plasticity in Turkish Commelina communis L. (Commelinaceae) populations. Turkish Journal of Botany, 22: 199-204.
  23. Lee, C. K., Fuse, S., Poopath, M., Pooma, R. and Tamura, M. N. (2022). Phylogenetics and infrafamilial classification of Commelinaceae (Commelinales). Botanical Journal of the Linnean Society, 198: 117-130. https://doi.org/10.1093/botlinnean/boab047
  24. Li, J., Zhang, W., Zhou, H., Yu, C. and Li, Q. (2024). Weed detection in soybean fields using improved YOLOv7 and evaluating herbicide reduction efficacy. Frontiers in Plant Science, 14: 1284338.
  25. Liu, Y., Yu, Q., and Geng, S. (2024). Real-time and lightweight detection of grape diseases based on Fusion Transformer YOLO. Frontiers in Plant Science, 15: 1269423. https://doi.org/10.3389/fpls.2024.1269423
  26. Medojević, S. (2024). Potato leaf disease detection using Faster R-CNN and YOLO models. International Journal of Multidisciplinary Studies and Innovative Technologies, 8(2): 144–150.
  27. Mill, R. R. and Tan, K. (1984). Commelinaceae. In: Flora of Turkey and the East Aegean Islands, Ed(s): Davis, P. H., Edinburgh University Press, U. K. http://www.jstor.org/stable/10.3366/j.ctvxcrhhs.30
  28. Osorio, K., Puerto, A., Pedraza, C., Jamaica, D. and Rodríguez, L. (2020). A deep learning approach for weed detection in lettuce crops using multispectral images. AgriEngineering, 2: 471-488. https://doi.org/10.3390/agriengineering2030032
  29. Pei, H., Sun, Y., Huang, H., Zhang, W., Sheng, J. and Zhang, Z. (2022). Weed detection in maize fields by UAV images based on crop row preprocessing and improved YOLOv4. Agriculture, 12(7): 975. https://doi.org/10.3390/agriculture12070975
  30. Quénéhervé, P., Chabrier, C., Auwerkerken, A., Topart, P., Martiny, B. and Marie-Luce, S. (2006). Status of weeds as reservoirs of plant parasitic nematodes in banana fields in Martinique. Crop Protection, 25(8): 860-867. https://doi.org/10.1016/j.cropro.2005.11.009
  31. Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. IEEE Conference on Computer Vision and Pattern Recognition, 27-30 June, P. 779-788, Las Vegas, U. S. A.
  32. Rodríguez-Lira, D. C., Córdova-Esparza, D. M., Álvarez-Alvarado, J. M., Romero-González, J. A., Terven, J. and Rodríguez-Reséndiz, J. (2024). Comparative analysis of YOLO models for bean leaf disease detection in natural environments. AgriEngineering, 6(4): 4585-4603. https://doi.org/10.3390/agriengineering6040262
  33. Sarvestani, G. S., Edalat, M., Shirzadifar, A. and Pourghasemi, H. R. (2025). Early season dominant weed mapping in maize field using unmanned aerial vehicle (UAV) Imagery: Towards developing prescription map. Smart Agricultural Technology, 11: 100956. https://doi.org/10.1016/j.atech.2025.100956
  34. Soeb, M. J. A., Jubayer, M. F., Tarin, T. A., Al Mamun, M. R., Ruhad, F. M., Parven, A., Mubarak, N. M., Karri, S. L. and Meftaul, I. M. (2023). Tea leaf disease detection and identification based on YOLOv7 (YOLO-T). Scientific Reports, 13: 6078. https://doi.org/10.1038/s41598-023-33270-4
  35. Stark, T., Stefan, V., Wurm, M., and Spanier, R., Taubenböck, H. and Knight, T. M. (2023). YOLO object detection models can locate and classify broad groups of flower-visiting arthropods in images. Scientific Reports, 13, 16364. https://doi.org/10.1038/s41598-023-43482-3
  36. Sun, T., Cui, L., Zong, L., Zhang, S., Jiao, Y., Xue, X. and Jin, Y. (2024). Weed recognition at soybean seedling stage based on YOLOV8nGP + NExG algorithm. Agronomy, 14: 657. https://doi.org/10.3390/agronomy14040657
  37. Sunil, G. C., Upadhyay, A., Zhang, Y., Howatt, K., Peters, T., Ostlie, M., Aderholdt, W. and Sun, X. (2024). Field-based multispecies weed and crop detection using ground robots and advanced YOLO models: A data and model-centric approach. Smart Agricultural Technology, 9:100538. https://doi.org/10.1016/j.atech.2024.100538
  38. Tripathi, A., Gohokar, V. and Kute, R. (2024). Comparative analysis of YOLOv8 and YOLOv9 models for real-time plant disease detection in hydroponics. Engineering, Technology and Applied Science Research, 14: 17269-17275. https://doi.org/10.48084/etasr.8301
  39. Türker, O. and Çoruh, İ. (2021). Bayburt İli fasulye ekim alanlarında görülen yabancı otlar, yoğunlukları ve rastlama sıklıkları. Tekirdağ Ziraat Fakültesi Dergisi, 20(3): 542-549.
  40. Ulloa, S. M. and Owen, M. D. K. (2009). Response of Asiatic Dayflower (Commelina communis) to glyphosate and alternatives in soybean. Weed Science, 57(1): 74-80.
  41. University of Colorado Museum of Natural History (1954). Herbarium specimen (Barcode No. 02025195). COLO Herbarium. https://botanydb.colorado.edu/taxa/index.php?tid=129050&taxauthid=1&clid=17556 (Accessed Date: 08.03.2025).
  42. Uygun, T., Özgüven, M. M. and Yanar, D. (2024). Detection of damage caused by some vineyard pests with the YOLOv8x model using deep learning and object detection methods. Turkish Journal of Agriculture - Food Science and Technology, 12(3): 386-396. https://doi.org/10.24925/turjaf.v12i3.386-396.6510
  43. Wang, J., Qi, Z., Wang, Y. and Liu, Y. (2025). A lightweight weed detection model for cotton fields based on an improved YOLOv8n. Scientific Reports, 15: 457. https://doi.org/10.1038/s41598-024-84748-8
  44. Wang, Q., Cheng, M., Huang, S., Cai, Z., Zhang, J. and Yuan, H. (2022). A deep learning approach incorporating YOLOv5 and attention mechanisms for field real-time detection of the invasive weed Solanum rostratum Dunal seedlings. Computers and Electronics in Agriculture, 199: 107194. https://doi.org/10.1016/j.compag.2022.107194
  45. Xinming, W. and Tang, S. (2023). Comparative study on leaf disease identification using YOLOv4 and YOLOv7 algorithm. AgBioForum, 25(1): 58-67.
  46. Yang, J., Wang, Y., Chen, Y. and Yu, L. (2022). Detection of weeds growing in Alfalfa using convolutional neural networks. Agronomy, 12(6): 1459 https://doi.org/10.3390/agronomy12061459
  47. Yang, J., Yu, H., Cui, H., Chen, J., and Li, X. (2021). High antioxidant ability confer resistance to atrazine in Commelina communis L. Plants, 10(12): 2685. https://doi.org/10.3390/plants10122685
  48. Yazlık, A., Çöpoğlu, E., Özçelik, A., Tembelo, B., Yiğit, M., Albayrak, B., Baykuş, M. A. and Aydınlı, V. (2019). Weed Species and Their Impacts: Fruit Nursery Area Sample in Düzce. Journal of Tekirdag Agricultural Faculty, 16(3): 389-401. https://doi.org/10.33462/jotaf.578999
  49. Ying, B., Xu, Y., Zhang, S., Shi, Y. and Liu, L. (2021). Weed detection in images of carrot fields based on improved YOLOv4. Trait. du Signal, 38: 341-348. https://doi.org/10.18280/TS.380211
  50. Zhu, J., Qiu, J., Chen, S., Chen, S. and Zhang, H. (2025). An application of YOLOv8 integrated with attention mechanisms for detection of grape leaf black rot spots. PLoS One, 20(4): e0321788. https://doi.org/10.1371/journal.pone.0321788