Klasifikasi Multi Penyakit Tanaman Pepaya Berdasarkan Citra Daun Berbasis Deep Learning Menggunakan Convolutional Neural Network (CNN)
Abstract
Penyakit pada tanaman pepaya seperti Anthracnose, Bacterial Spot, Curl, dan Ring Spot dapat menurunkan produktivitas dan kualitas hasil panen secara signifikan. Keterbatasan metode konvensional yang mengandalkan pengamatan visual secara manual menyebabkan proses identifikasi penyakit menjadi tidak konsisten, memakan waktu lama, dan sulit diterapkan pada skala lahan pertanian yang luas. Penelitian ini bertujuan untuk mengembangkan model deep learning berbasis Convolutional Neural Network (CNN) guna mengklasifikasikan lima kategori kondisi daun pepaya secara akurat. Metodologi yang digunakan meliputi pemanfaatan dataset BDPapayaLeaf yang berisi 2.159 citra asli, yang kemudian diekspansi menjadi 6.477 citra menggunakan teknik augmentasi data. Model dilatih menggunakan pembagian data 70:15:15 (latih, validasi, uji) dengan memanfaatkan metode transfer learning, optimizer Adam, dan mekanisme early stopping. Hasil pengujian menunjukkan bahwa model PapayaLeafCNN yang diusulkan berhasil mencapai akurasi keseluruhan sebesar 84,66% dan weighted average F1-score sebesar 84,82% pada data uji. Analisis per kelas menunjukkan performa tertinggi pada kelas daun sehat (Healthy) dengan F1-score 94,29%, sementara kelas Bacterial Spot mencatatkan performa terendah (76,54%) akibat tingginya tingkat kesalahan prediksi yang tumpang tindih dengan kelas Curl. Secara keseluruhan, model CNN yang diusulkan mampu melakukan klasifikasi multi-penyakit daun pepaya dengan baik, meski ke depannya tetap diperlukan strategi khusus untuk mengklasifikasikan penyakit dengan kemiripan visual yang tinggi.
Keywords
Full Text:
PDFReferences
Aboelenin, S., F. A. Elbasheer, M. M. Eltoukhy, W. M. El-Hady, & K. M. Hosny. 2025. A hybrid framework for plant leaf disease detection and classification using convolutional neural networks and vision transformer, Complex & Intelligent Systems, vol. 11, Art. 142.
Ahmed, F., dkk. 2023. Machine Learning-Based Tea Leaf Disease Detection: A Comprehensive Review, ArXiv / Springer.
Ashtagi, R., dkk. 2025. Image preprocessing permits the machine learning model to concentrate on the main features, Journal of Agronomy.
Banarase, S. J. & S. D. Shirbahadurkar. 2024. Enhancing papaya leaf disease detection with CNN and transfer learning fusion for precise disease diagnosis, Journal of Electrical Systems, vol. 20, no. 2s, pp. 1015–1024.
Brahimi, M., dkk. 2023. Deep learning for plant diseases: Classification and symptoms visualization in modern agriculture, Applied Artificial Intelligence.
Chen, C., dkk. 2025. Edge computing and lightweight convolutional neural networks for real-time papaya leaf disease detection, Artificial Intelligence in Agriculture, vol. 7, pp. 234-245.
Gani, R., dkk. 2025. Attention guided convolutional neural network with explainable AI for papaya leaf disease detection in edge and drone agricultural systems, Scientific Reports, vol. 15, Art. 41489.
Hurtado, J., dkk. 2023. Traditional algorithms to eliminate scene changes from recognition results in natural environments, IEEE Access.
Hasan, M. K., dkk. 2023. Overcoming class imbalance in agricultural image classification using advanced data augmentation techniques, Computers and Electronics in Agriculture, vol. 210, Art. 108040.
Isty, M. N., dkk. 2023. A comprehensive review on Plant Leaf Disease detection using Deep learning, ArXiv.
Kamilaris, A. & F. X. Prenafeta-Boldú. 2022. Deep learning in agriculture: A comprehensive review and recent advancements, Computers and Electronics in Agriculture.
Kaur, K., dkk. 2024. Experimental Evaluation of Deep Learning Based Plant Leaf Disease Detection System, SciTePress.
Karthikeyan, S., R. Charan, S. Narayanan, & L. J. Anbarasi. 2025. Enhanced plant disease classification with attention-based convolutional neural network using squeeze and excitation mechanism, Frontiers in Artificial Intelligence, vol. 8, Art. 1640549.
Kim, D. W. & S. Lee. 2025. Integration of IoT and deep learning for automated plant disease monitoring in smart greenhouses, IEEE Internet of Things Journal, vol. 13, no. 4, pp. 4501-4512.
Kiobia, L., dkk. 2023. Pest infestations require broader criteria for detection, identification, and segmentation, Smart Agricultural Technology.
Madhurya & Jubilson. 2025. Performance Evaluation of Hybrid Deep Learning Architectures for Plant Disease and Severity Classification, EPJ Web of Conferences.
Maity, S., dkk. 2023. Automating pest and disease detection using labeled training data, Expert Systems with Applications.
Mir, T. A., dkk. 2024. Hybridized Model for Improved Papaya Leaf Disease Classification: CNN and Random Forest Integration, IEEE Xplore.
Mustofa, S., M. T. Ahad, Y. R. Emon, & A. Sarker. 2024. BDPapayaLeaf: A dataset of papaya leaf for disease detection, classification, and analysis, Data in Brief, vol. 57, Art. 110910.
Nikith, B. V., dkk. 2023. Deep learning methodologies for plant disease diagnosis and severity estimation, Journal of Crop Science.
Parashar, A., dkk. 2024. Thorough review of various yield prediction models, analyzing their advancements, Artificial Intelligence in Agriculture.
Rahman, A., dkk. 2024. Real-time deployment of lightweight CNN models for tropical plant disease diagnosis on mobile devices, Journal of Smart Agriculture, vol. 5, no. 2, pp. 112-125.
Saad, M. & A. Salman. 2025. One-shot learning techniques with field images for large labeled datasets in agriculture, Computers and Electronics in Agriculture.
Shandilya, G., S. Gupta, H. G. Mohamed, S. Bharany, A. U. Rehman, & S. Hussen. 2025. Enhanced maize leaf disease detection and classification using an integrated CNN-ViT model, Food Science & Nutrition, vol. 13, Art. e70513.
Sharma, R., dkk. 2024. Transfer learning approaches for the detection of foliar diseases in papaya and mango crops, Frontiers in Plant Science, vol. 15, Art. 134567.
Shoaib, M., dkk. 2023. Detection of diseases and pest infestation in plants using machine learning models and computer vision techniques, Frontiers in Plant Science.
Sofuoglu, C. I., dkk. 2024. A robust model requiring large, diverse and balanced dataset for plant leaf disease, International Journal of Remote Sensing.
Suryavanshi, S., dkk. 2024. Agricultural AI: Integrating Federated Learning and CNN in Papaya Leaf Disease Detection, IEEE Xplore.
Vishnoi, V., dkk. 2023. Effectiveness of CNNs in identifying diseases in apple plants based on leaf images, Multimedia Tools and Applications.
Xiong, Y., dkk. 2024. Computer-vision-based methods combined with traditional image processing techniques and classifiers to detect plant diseases, Journal of Agricultural Informatics.
Refbacks
- There are currently no refbacks.
