TY - JOUR T1 - TARIMSAL SENSÖR VERİLERİ KULLANILARAK BİTKİ HASTALIKLARININ ERKEN TESPİTİ İÇİN LSTM TABANLI DERİN ÖĞRENME MODELİ TT - CROP DISEASES USING AGRICULTURAL SENSOR DATA LSTM-BASED DEEP LEARNING MODEL FOR EARLY DETECTION AU - Genç, Elif AU - Bağlum, Cem AU - Çağlar, Osman AU - Kartal, Yusuf AU - Seke, Erol AU - Özkan, Kemal PY - 2025 DA - April Y2 - 2025 DO - 10.31796/ogummf.1529025 JF - Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi JO - ESOGÜ Müh Mim Fak Derg PB - Eskişehir Osmangazi University WT - DergiPark SN - 2630-5712 SP - 1712 EP - 1720 VL - 33 IS - 1 LA - tr AB - Bitki hastalıklarının güvenilir ve zamanında tanımlanması modern tarımda çok önemli bir zorluktur. Geleneksel yöntemler gözle görülür semptomların manuel olarak gözlemlenmesine dayanır. Görünür semptomlar, enfeksiyonun orta veya geç aşamalarında ortaya çıkma eğilimindedir; bu da yayılma veya verim azalması olasılığını artırır. Bitki hastalıkları gözle görülebilir hale geldikten sonra hastalık bulaşmış olmakta ve tedavi için geç kalınmış olmaktadır. Bu sebeplerden dolayı bitki hastalıkların gözle görülmeden önce tespit edilebilmesi için daha düşük maliyetli olan çözümlere ihtiyaç vardır. Bu çalışmada, serada yetiştirilen hıyar bitkilerinde ortaya çıkabilecek virüs etkilerinin derin öğrenme ve yapay zeka uygulamaları yardımıyla erken dönemde tespit edilmesi hedeflenmiştir. Bu amaçla bitki hastalıklarının erken tespiti için LSTM tabanlı bir derin öğrenme modeli önerilmiştir. Bu modelde kullanılan veriler için, hastalık inoküle edilen ve sağlıklı bitkilerin bulunduğu iklim odaları kurulmuştur ve toprak sensörleri kullanılarak hıyar bitkisinden zamansal veriler toplanmıştır. Daha sonra veri hazırlama süreci içerisinde verilerin temizlenmesi, özniteliklerinin çıkarılması ve etiketleme gibi işlemler yapılmıştır. Eğitim aşamasından sonra model, tarımsal sensörlerden gelen zaman serisi verilerini analiz ederek anomali tespiti yapabilmekte, bu sayede bitki hastalıkların görsel belirtileri ortaya çıkmadan hastalıklı olduklarını söylemektedir. Modelin performansını değerlendirmek için doğruluk, sınıflandırma raporu, karışıklık matrisi gibi metrikler kullanılmıştır. Elde edilen sonuçlar oldukça başarılı; model %99.95 doğruluk sağlamış ve anomali tespiti konusunda yüksek başarı göstermiştir. Yapılan çalışma sonucunda bitki hastalıkların erken tespiti ile minimum zirai ilaçlama ile maliyet düşürücü tedbirler en üst seviyede alınabilecek insan ve çevre maksimum seviyede korunmuş olacaktır. KW - Bitki Hastalıkları KW - Erken Tespit KW - Toprak Sensörleri KW - LSTM KW - Salatalık N2 - Reliable and timely identification of plant diseases is a crucial challenge in modern agriculture. Traditional methods rely on manual observation of visible symptoms. Visible symptoms tend to appear in the middle or late stages of infection, which increases the likelihood of spread or yield reduction. Once plant diseases become visibly detectable, the infection has already occurred, and it may be too late for effective treatment. Therefore, cost-effective solutions are needed to detect plant diseases before they become visually apparent. This study aims to detect the effects of viruses on cucumber plants grown in greenhouses at an early stage using deep learning and artificial intelligence applications For this purpose, an LSTM-based deep learning model for early detection of plant diseases is proposed. To collect data for the model, climate chambers housing both diseased and healthy plants were established, and temporal data were gathered from cucumber plants using soil sensors. During the data preparation process, steps such as data cleaning, feature extraction, and labeling were performed. After the training phase, the model can analyze time-series data from agricultural sensors to detect anomalies, identifying diseased plants before visual symptoms appear. Metrics such as accuracy, classification report and confusion matrix were used to evaluate the performance of the model. The results obtained are quite successful; the model achieved 99.95% accuracy and showed high success in anomaly detection. As a result of the study, with the early detection of plant diseases, cost-reducing measures can be taken at the highest level with minimum pesticides, and humans and the environment will be protected at the maximum level. CR - Abade, A., Ferreira, P. A. ve Vidal, F. B. (2021). Plant diseases recognition on images using convolutional neural networks: A systematic review. Computers and Electronics in Agriculture, 185, 106125. doi: https://doi.org/10.1016/j.compag.2021.106125 CR - Abdu, A. M., Mokji, M. M. ve Sheikh, U. U. (2020). Machine learning for plant disease detection: An investigative comparison between support vector machine and deep learning. IAES International Journal of Artificial Intelligence (IJ-AI), 9(4), 670-683. doi: https://doi.org/10.11591/ijai.v9.i4.pp670-683 CR - Akbaş, B. (2019). Bitki sağlığının sürdürülebilir tarımdaki yeri. Ziraat Mühendisliği (368), 6-13. doi: https://doi.org/10.33724/zm.606199 CR - Ashwini, C. ve Sellam, V. (2024). An optimal model for identification and classification of corn leaf disease using hybrid 3D-CNN and LSTM. Biomedical Signal Processing and Control, 92, 106089, ISSN 1746-8094. doi: https://doi.org/10.1016/j.bspc.2024.106089 CR - Barbedo, J. G. A. (2016). A review on the main challenges in automatic plant disease identification based on visible range images. Biosystems Engineering, 144, 52-60. doi: https://doi.org/10.1016/j.biosystemseng.2016.01.017 CR - Bischoff, V., Farias, K., Menzen, J. P. ve Pessin, G. (2021). Technological support for detection and prediction of plant diseases: A systematic mapping study. Computers and Electronics in Agriculture, 181, 105922. doi: https://doi.org/10.1016/j.compag.2020.105922 CR - Chin, P.-W., Ng, K.-W. ve Palanichamy, N. (2024). Plant disease detection and classification using deep learning methods: A comparison study. Journal of Informatics and Web Engineering, 3(1), 156-167. doi: https://doi.org/10.33093/jiwe.2024.3.1.10 CR - Cohen, B., Edan, Y., Levi, A. ve Alchanatis, V. (2022). Early detection of grapevine (vitis vinifera) downy mildew (peronospora) and diurnal variations using thermal imaging. Sensors 22, 3585. doi: https://doi.org/10.3390/s22093585 CR - Dyussembayev, K., Sambasivam, P., Bar, I., Brownlie, J. C., Shiddiky, M. J. A. ve Ford, R. (2021). Biosensor technologies for early detection and quantification of plant pathogens. Frontiers in Chemistry. doi: https://doi.org/10.3389/fchem.2021.636245 CR - Gao, R., Wang, R., Lu, F., Li, Q. ve Wu, H. (2021). Dual-branch, efficient, channel attention-based crop disease identification. Computers and Electronics in Agriculture 190, 106410. doi: https://doi.org/10.1016/j.compag.2021.106410 CR - Ferentinos, K. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311-318. doi: https://doi.org/10.1016/j.compag.2018.01.009 CR - Fischer, T. ve Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669. doi: https://doi.org/10.1016/j.ejor.2017.11.054 CR - Kelman, A., Pelczar, M. J., Pelczar, R. M. ve Shurtleff, M. C. (2023, December 28). Plant disease. Encyclopedia Britannica. Erişim adresi: https://www.britannica.com/science/plant-disease. CR - Lipton, Z. C., Kale, D. C., Elkan, C. ve Wetzel, R. (2015). Learning to diagnose with LSTM recurrent neural networks. arXiv Preprint arXiv:1511.03677. doi: https://doi.org/10.48550/arXiv.1511.03677 CR - Lu, Y., Chen, D., Olaniyi, E. ve Huang, Y. (2022). Generative adversarial networks (gans) for image augmentation in agriculture: A systematic review. Computers and Electronics in Agriculture 200, 107208. doi: https://doi.org/10.1016/j.compag.2022.107208 CR - Jackulin, C. ve Murugavalli, S. (2022). A comprehensive review on detection of plant disease using machine learning and deep learning approaches. Measurement: Sensors, 24, 100441, ISSN 2665-9174. doi: https://doi.org/10.1016/j.measen.2022.100441 CR - Mohanty, S. P., Hughes, D. P. ve Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419. doi: https://doi.org/10.3389/fpls.2016.01419 CR - Nguyen, C., Sagan V., Maimaitiyiming, M., Maimaitijiang, M., Bhadra, S. ve Kwasniewski, M. (2021). Early detection of plant viral disease using hyperspectral imaging and deep learning. Sensors, 21, 742. doi: https://doi.org/10.3390/s21030742 CR - Patel, P. (2021). A review on plant disease diagnosis through biosensor. International Journal of Biosensors and Bioelectronics, 7, 50-52. doi: https://doi.org/10.15406/ijbsbe.2021.07.00212 CR - Radovanović, D. ve Đukanovic, S. (2020), Image-based plant disease detection: a comparison of deep learning and classical machine learning algorithms, 24th International Conference on Information Technology (IT), Zabljak, Montenegro, 2020, 1-4. doi: https://doi.org/10.1109/IT48810.2020.9070664 CR - Sharma, V., Tripathi, A.K. ve Mittal, H., (2022). Technological revolutions in smart farming: current trends, challenges and future directions. Computers and Electronics in Agriculture 201, 107217. doi: https://doi.org/10.1016/j.compag.2022.107217 CR - Shin, J., Chang, Y. K., Heung, B., Nguyen-Quang, T., Price, G. W. ve Al-Mallahi, A. (2021). A deep learning approach for RGB image-based powdery mildew disease detection on strawberry leaves. Computers and Electronics in Agriculture 183, 106042. doi: https://doi.org/10.1016/j.compag.2021.106042 CR - Smetanin, A., Uzhinskiy, A., Ososkov, G., Goncharov, P. ve Nechaevskiy, A. (2021). Deep learning methods for the plant disease detection platform. AIP Conference Proceedings, 2377, 060006. doi: https://doi.org/10.1063/5.0068797 CR - Sutskever, I., Vinyals, O. ve Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in Neural Information Processing Systems, 27. doi: https://doi.org/10.48550/arXiv.1409.3215 CR - Terentev, A., Dolzhenko, V., Fedotov, A. ve Eremenko, D. (2022). Current state of hyperspectral remote sensing for early plant disease detection: A review. Sensors 22, 757. doi: https://doi.org/10.3390/s22030757 CR - Thakur, P.S., Khanna, P., Sheorey, T. ve Ojha, A. (2022). Trends in vision-based machine learning techniques for plant disease identification: A systematic review. Expert Syst Appl 208, 118117. doi: https://doi.org/10.1016/j.eswa.2022.118117 CR - Thomas, V., Maria, B., Patricia, G., Guillem, S., Isabel, T., Iker, A., Shawn, K. ve Araus, J. (2024). Comparing high-cost and lower-cost remote sensing tools for detecting pre-symptomatic downy mildew (Pseudoperonospora cubensis) infections in cucumbers. Computers and Electronics in Agriculture, 218, 108736. doi: https://doi.org/10.1016/j.compag.2024.108736 UR - https://doi.org/10.31796/ogummf.1529025 L1 - https://dergipark.org.tr/en/download/article-file/4126115 ER -