Tren dan Tantangan Deep Learning untuk Identifikasi Penyakit Daun Padi: Tinjauan Literatur Sistematis
DOI:
https://doi.org/10.54259/satesi.v6i1.7665Kata Kunci:
Deep Learning, Rice Leaf Disease, Convolutional Neural Network, Systematic Literature ReviewAbstrak
Perkembangan teknologi deep learning telah memberikan kontribusi signifikan dalam bidang pertanian, khususnya dalam identifikasi penyakit daun padi berbasis citra. Penelitian ini bertujuan untuk menganalisis tren perkembangan, performa model, serta tantangan dalam penerapan metode deep learning melalui pendekatan Systematic Literature Review (SLR). Proses kajian dilakukan dengan mengacu pada pedoman PRISMA, dengan menganalisis 10 artikel ilmiah yang dipublikasikan dalam rentang tahun 2020–2026. Hasil penelitian menunjukkan bahwa Convolutional Neural Network (CNN) masih menjadi metode yang paling dominan digunakan, dengan berbagai variasi arsitektur seperti ResNet, VGG, dan MobileNet. Selain itu, terdapat perkembangan menuju metode yang lebih adaptif, seperti object detection berbasis YOLO dan model hybrid yang menggabungkan CNN dengan Vision Transformer. Sebagian besar penelitian melaporkan tingkat akurasi di atas 90%, yang menunjukkan potensi besar deep learning dalam mendukung deteksi penyakit tanaman secara otomatis.
Namun demikian, analisis lebih lanjut mengungkap adanya kesenjangan antara performa model pada dataset terkontrol dan kondisi dunia nyata. Tantangan utama yang diidentifikasi meliputi keterbatasan dataset yang representatif, rendahnya kemampuan generalisasi model, tingginya kompleksitas komputasi, serta kurangnya interpretabilitas sistem. Selain itu, implementasi di lapangan masih terbatas, sehingga menunjukkan perlunya penelitian lanjutan yang lebih aplikatif. Penelitian ini memberikan kontribusi dalam bentuk pemetaan komprehensif terhadap perkembangan metode, serta identifikasi research gap yang dapat menjadi dasar bagi pengembangan sistem deteksi penyakit tanaman yang lebih robust dan aplikatif di masa depan.
Unduhan
Referensi
S. Akter, R. I. Sumon, H. Ali, and H. C. Kim, “Utilizing convolutional neural networks for the effective classification of rice leaf diseases through a deep learning approach,” Electronics, vol. 13, no. 20, p. 4095, 2024. https://doi.org/10.3390/electronics13204095
C. Dewi, F. Y. Bilaut, H. J. Christanto, and G. Dai, “Deep learning for the classification of rice leaf diseases using YOLOv8,” 2024. https://doi.org/10.18280/mmep.111115
T. P. Pavithra and B. Baranidharan, “A hybrid ViT–CNN model premeditated for rice leaf disease identification,” Int. J. Comput. Model. Electr. Netw., vol. 12, no. 1, 2024.
https://doi.org/10.18280/ijcmem.120104
X. Bi and H. Wang, “Double-branch deep convolutional neural network-based rice leaf diseases recognition and classification,” Journal of Agricultural Engineering, vol. 55, no. 1, 2024. https://doi.org/10.4081/jae.2023.1544
M. T. Ahad, Y. Li, B. Song, and T. Bhuiyan, “Comparison of CNN-based deep learning architectures for rice diseases classification,” Artificial Intelligence in Agriculture, vol. 9, pp. 22–35, 2023. https://doi.org/10.1016/j.aiia.2023.07.00
J. Arcila-Diaz, D. Altamirano-Chavez, L. Arcila-Diaz, and C. Valdivia, “Real-time identification of rice leaf diseases using convolutional neural networks,” International Journal of Computing, vol. 23, no. 4, pp. 709–714, 2024. https://doi.org/10.47839/ijc.23.4.3773
R. Gahane, “Rice Leaf Disease Detection and Remedies using Deep Learning”, Int J Intell Syst Appl Eng, vol. 12, no. 4, pp. 3380 –, Jun. 2024.
R. Tiwari and N. Vora, “Enhancing paddy leaf disease classification using CNN and MobileNetV2,” Journal of Soft Computing Paradigm, vol. 6, no. 3, pp. 324–340, 2024. https://doi.org/10.36548/jscp.2024.3.008
B. S. Bari et al., “A real-time approach of diagnosing rice leaf disease using deep learning-based faster R-CNN framework,” PeerJ Computer Science, vol. 7, p. e432, 2021. https://doi.org/10.7717/peerj-cs.432
M. Dutta et al., “Rice leaf disease classification—A comparative approach using convolutional neural network (CNN), cascading autoencoder with attention residual U-net (CAAR-U-Net), and MobileNet-V2 architectures,” Technologies, vol. 12, no. 11, p. 214, 2024. https://doi.org/10.3390/technologies12110214
D. Moher, A. Liberati, J. Tetzlaff, D. G. Altman, and PRISMA Group, “Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement,” International Journal of Surgery, vol. 8, no. 5, pp. 336–341, 2010. https://doi.org/10.1016/j.ijsu.2010.02.007
B. Kitchenham and S. Charters, Guidelines for performing systematic literature reviews in software engineering, EBSE Technical Report, ver. 2.3, 2007.
H. Snyder, “Literature review as a research methodology: An overview and guidelines,” Journal of Business Research, vol. 104, pp. 333–339, 2019. https://doi.org/10.1016/j.jbusres.2019.07.039
M. Sharma, C. J. Kumar, and D. K. Bhattacharyya, “Machine/deep learning techniques for disease and nutrient deficiency disorder diagnosis in rice crops: A systematic review,” Biosystems Engineering, vol. 244, pp. 77–92, 2024. https://doi.org/10.1016/j.biosystemseng.2024.05.014
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Maliatul Fitriyasari
Artikel ini berlisensi Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
