Ayçiçeğinde Küllemenin Makine Öğrenimine Dayalı Tespiti ve Şiddetinin Değerlendirilmesi: Hassas Tarım Yaklaşımı

Yıl 2023, Cilt: 37 Sayı: 2, 387 - 400, 08.12.2023

Alperen Kaan Bütüner , Yavuz Selim Şahin , Atilla Erdinç , Hilal Erdoğan

https://doi.org/10.20479/bursauludagziraat.1340129

Cited By: 2

Öz

Ayçiçeğinde külleme (Golovinomyces cichoracearum (DC.) V.P. Heluta), önemli ölçüde verim kaybına
neden olan, ayçiçeği ürünleri için önemli bir tehdittir. Geleneksel teşhis yöntemleri, insan gözlemine dayalı
olarak, erken hastalık tespiti ve hızlı kontrol sağlama konusunda yetersiz kalmaktadır. Bu çalışma, ayçiçeğinde küllemenin erken tespiti için makine öğrenimini kullanarak bu soruna yeni bir yaklaşım sunmaktadır. Orijinal alan görüntülerinden elde edilen fotoğraflara ait toprak, külleme, sap ve yaprak matrisleri ile Decision Trees (Karar Ağaçları) modeli eğitilerek hastalık şiddet seviyeleri tespit edilmiştir. Test görüntülerinde sırasıyla A ve C olarak etiketlenmiş hastalık şiddeti seviyeleri %18.14 ve %5.56 olarak belirlenmiştir. Modelin %85 oranında gösterdiği doğruluk, modelin yüksek düzeyde yetkinliğe ve özellikle Decision Trees modelinin tarım alanında hastalık kontrolünü ve hastalıkların önlenmesini devrimleştirmek için umut verici perspektiflere sahip olduğunu göstermektedir.

Anahtar Kelimeler

Karar ağaçları, makine öğrenimi, külleme, ayçiçeği, Hastalık şiddeti

Machine Learning-Based Detection and Severity Assessment of Sunflower Powdery Mildew: A Precision Agriculture Approach

Öz

Sunflower powdery mildew (Golovinomyces cichoracearum (DC.) V.P. Heluta) is a substantial threat
to sunflower crops, causing significant yield loss. Traditional identification methods, based on human
observation, fall short in providing early disease detection and quick control. This study presents a novel
approach to this problem, utilizing machine learning for the early detection of powdery mildew in sunflowers. The disease severity levels were determined by training a Decision Trees model using matrix of soil, powdery mildew, stems, and leaf images obtained from original field images. It was detected disease severity levels of 18.14% and 5.56% in test images labeled as A and C, respectively. The model's demonstrated accuracy of 85% suggests high proficiency, indicating that machine learning, specifically the DTs model, holds promising prospects for revolutionizing disease control and diseases prevention in agriculture.

Anahtar Kelimeler

Decision trees, disease severity, machine learning, powdery mildew, sunflower

Kaynakça

• Adi, K., Pujiyanto, S., Dwi Nurhayati, O. and Pamungkas, A. 2017. Beef quality identification using thresholding method and decision tree classification based on android smartphone. Journal of Food Quality, 9: 1-10.
• Bock, C. H., Barbedo, J. G., Del Ponte, E. M., Bohnenkamp, D. and Mahlein, A. K. 2020. From visual estimates to fully automated sensor-based measurements of plant disease severity: status and challenges for improving accuracy. Phytopathology Research, 2(1): 1-30.
• Bock, C. H., Poole, G. H., Parker, P. E. and Gottwald, T. R. 2010. Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging. Critical reviews in plant sciences, 29(2): 59-107.
• Cai, J., Xiao, D., Lv, L. and Ye, Y. 2019. An early warning model for vegetable pests based on multidimensional data. Computers and Electronics in Agriculture, 156: 217-226.
• Cook, R. T. A. and Braun, U. 2009. Conidial germination patterns in powdery mildews. Mycological Research 113(5): 616-636.
• Dawod, R. G. and Dobre, C. 2021. Classification of Sunflower Foliar Diseases Using Convolutional Neural Network. 23rd International Conference on Control Systems and Computer Science (CSCS). Bucharest, Romania. pp. 476-481
• Dokken, K. M. and Davis, L. C. 2007. Infrared imaging of sunflower and maize root anatomy. Journal of agricultural and food chemistry, 55(26): 10517-10530.
• Erdoğan, H., Bütüner, A. K. and Şahin, Y. S. 2023. Detection of Cucurbit Powdery Mildew, Sphaerotheca fuliginea (Schlech.) Polacci by Thermal Imaging in Field Conditions. Scientific Papers Series Management, Economic Engineering in Agriculture and Rural Development, 23(1): 189-192.
• Esgario, J. G., Krohling, R. A. and Ventura, J. A. 2020. Deep learning for classification and severity estimation of coffee leaf biotic stress. Computers and Electronics in Agriculture, 169: 105162.
• Gallardo-Romero, D. J., Apolo-Apolo, O. E., Martínez-Guanter, J. and Pérez-Ruiz, M. 2023. Multilayer Data and Artificial Intelligence for the Delineation of Homogeneous Management Zones in Maize Cultivation. Remote Sensing, 15(12): 3131-3148.
• Goncalves, J. P., Pinto, F. A., Queiroz, D. M., Villar, F. M., Barbedo, J. G. and Del Ponte, E. M. 2021. Deep learning architectures for semantic segmentation and automatic estimation of severity of foliar symptoms caused by diseases or pests. Biosystems Engineering, 210: 129-142.
• Jasim, S. S. and Al-Taei, A. A. M. 2018. A Comparison Between SVM and K-NN for classification of Plant Diseases. Diyala Journal for Pure Science, 14(2): 94-105.
• Ji, M., Zhang, K., Wu, Q. and Deng, Z. 2020. Multi-label learning for crop leaf diseases recognition and severity estimation based on convolutional neural networks. Soft Computing, 24: 15327-15340.
• Kaur, S., Pandey, S. and Goel, S. 2019. Plants disease identification and classification through leaf images: A survey. Archives of Computational Methods in Engineering, 26: 507-530.
• Khan, C. M. T., Ab Aziz, N. A., Raja, J. E., Nawawi, S. W. B. and Rani, P. 2022. Evaluation of Machine Learning Algorithms for Emotions Recognition using Electrocardiogram. Emerging Science Journal, 7(1), 147-161.
• Lebeda, A. and Mieslerová, B. 2011. Taxonomy, distribution and biology of lettuce powdery mildew (Golovinomyces cichoracearum sensu stricto). Plant Pathology 60(3): 400-415.
• Lee, H. C., Yoon, S. B., Yang, S. M., Kim, W. H., Ryu, H. G., Jung, C. W., Suh, K. S. and Lee, K. H. 2018. Prediction of acute kidney injury after liver transplantation: machine learning approaches vs. logistic regression model. Journal of clinical medicine, 7(11), 428.
• Lee, S. J., Chung, D., Asano, A., Sasaki, D., Maeno, M., Ishida, Y., Kobayashi, T., Kuwajima, Y., Da Silva, J. D. and Nagai, S. 2022. Diagnosis of tooth prognosis using artificial intelligence. Diagnostics, 12(6), 1422.
• Li, W., Wang, D., Li, M., Gao, Y., Wu, J. and Yang, X. 2021. Field detection of tiny pests from sticky trap images using deep learning in agricultural greenhouse. Computers and Electronics in Agriculture, 183: 106048.
• Lin, K., Gong, L., Huang, Y., Liu, C. and Pan, J. 2019. Deep learning-based segmentation and quantification of cucumber powdery mildew using convolutional neural network. Frontiers in plant science, 10: 155.
• Lindström, L. I. and Hernández, L. F. 2015. Developmental morphology and anatomy of the reproductive structures in sunflower (Helianthus annuus): a unified temporal scale. Botany, 93(5): 307-316.
• Liu, Y., Zhang, Y., Jiang, D., Zhang, Z. and Chang, Q. 2023. Quantitative Assessment of Apple Mosaic Disease Severity Based on Hyperspectral Images and Chlorophyll Content. Remote Sensing, 15(8): 2202-2020.
• Mahmood, R. A. R., Abdi, A. and Hussin, M. 2021. Performance evaluation of intrusion detection system using selected features and machine learning classifiers. Baghdad Science Journal, 18(2 (Suppl.)), 0884-0884.
• Malik, A., Vaidya, G., Jagota, V., Eswaran, S., Sirohi, A., Batra, I., Rakhra, M. and Asenso, E. 2022. Design and evaluation of a hybrid technique for detecting sunflower leaf disease using deep learning approach. Journal of Food Quality 2022: 12.
• Mulpuri, S., Soni, P. K. and Gonela, S. K. 2016. Morphological and molecular characterization of powdery mildew on sunflower (Helianthus annuus L.), alternate hosts and weeds commonly found in and around sunflower fields in India. Phytoparasitica, 44(3): 353-367.
• Nagasubramanian, K., Jones, S., Singh, A. K., Sarkar, S., Singh, A. and Ganapathysubramanian, B. 2019. Plant disease identification using explainable 3D deep learning on hyperspectral images. Plant methods, 15: 1-10.
• Owomugisha, G. and Mwebaze, E. 2016. Machine learning for plant disease incidence and severity measurements from leaf images. 15th IEEE international conference on machine learning and applications (ICMLA). Anaheim, CA, USA. pp. 158-163.
• Park, M. J., Kim, B. S., Choi, I. Y., Cho, S. E. and Shin, H. D. 2015. First report of powdery mildew caused by Golovinomyces ambrosiae on sunflower in Korea. Plant Disease, 99(4): 557-557.
• Pethybridge, S. J. and Nelson, S. C. 2015. Leaf Doctor: A new portable application for quantifying plant disease severity. Plant disease, 99(10): 1310-1316.
• Prabhakar, M., Purushothaman, R. and Awasthi, D. P. 2020. Deep learning based assessment of disease severity for early blight in tomato crop. Multimedia Tools and Applications, 79: 28773-28784.
• Reddy, K. P., Rao, S. C., Kirti, P. B. and Sujatha, M. 2013. Development of a scoring scale for powdery mildew (Golovinomyces cichoracearum (DC.) VP Heluta) disease and identification of resistance sources in cultivated and wild sunflowers. Euphytica, 190: 385-399.
• Şahin, Y. S., Erdinç, A., Bütüner, A. K. and Erdoğan, H. 2023. Detection of Tuta absoluta larvae and their damages in tomatoes with deep learning-based algorithm. International Journal of Next-Generation Computing, 14(3): 555-565.
• Singh, A., Ganapathysubramanian, B., Singh, A. K. and Sarkar, S. 2016. Machine learning for high-throughput stress phenotyping in plants. Trends in plant science, 21(2): 110-124.
• Troisi, M., Bertetti, D., Garibaldi, A. and Gullino, M. L. 2010. First report of powdery mildew caused by Golovinomyces cichoracearum on Gerbera (Gerbera jamesonii) in Italy. Plant disease, 94(1): 130-130.
• Wang, G., Sun, Y. and Wang, J. 2017. Automatic image-based plant disease severity estimation using deep learning. Computational intelligence and neuroscience, 2017: 1-8.
• Wu, Q., Zeng, J. and Wu, K. 2022. Research and application of crop pest monitoring and early warning technology in China. Frontiers of Agricultural Science and Engineering, 9(1): 19-36.