Peningkatan Akurasi Deteksi Penyakit Daun Padi Menggunakan Augmentasi Data Berbasis Generative Adversarial Networks (GAN)

Nasya Sunia Tubuon; Nancy Jeane Tuturoong; Salaki Reynaldo Joshua

doi:10.30606/rjti.v5i2.4585

Authors

Nasya Sunia Tubuon Universitas Sam Ratulangi
Nancy Jeane Tuturoong Universitas Sam Ratulangi
Salaki Reynaldo Joshua Universitas Sam Ratulangi

DOI:

https://doi.org/10.30606/rjti.v5i2.4585

Keywords:

Data augmentation, rice leaf disease, GAN, EfficientNetB0, StyleGAN2-ADa

Abstract

Rice is a staple food crop for more than half of the global population, with Asia contributing approximately 90% of global production. Leaf diseases, particularly Blast and Bacterial Blight, are major factors contributing to reduced rice productivity in Indonesia. Conventional detection methods based on visual observation are often subjective and time-consuming, highlighting the need for more reliable automated detection systems. This study aims to implement StyleGAN2-ADA to generate synthetic rice leaf disease images and evaluate its impact on the performance of Convolutional Neural Network-based classification. This research employed a quantitative experimental approach by comparing two scenarios: Baseline without GAN augmentation and Proposed with StyleGAN2-ADA synthetic image augmentation. Two CNN architectures, EfficientNetB0 and ResNet50, were evaluated using accuracy, precision, recall, F1-Score, and confusion matrix metrics. The quality of synthetic images was assessed using the Fréchet Inception Distance. The results demonstrated that StyleGAN2-ADA augmentation improved the overall F1-Score of EfficientNetB0 from 97.62% to 98.20%, with the largest improvement observed in the Blight class, increasing by 3.11%. For ResNet50, the overall F1-Score increased from 97.60% to 98.20%, although the Blast class showed no performance improvement after augmentation. GAN augmentation provided the most consistent benefits for the minority Blight class, while its impact on the Blast class varied across metrics. In EfficientNetB0, improvements in precision and F1-Score were accompanied by a decrease in recall. These findings indicate that model evaluation should consider class-specific performance and the trade-off between precision and recall rather than relying solely on aggregate metrics

Downloads

Download data is not yet available.

References

N. K. FUKAGAWA and L. H. ZISKA, “Rice: Importance for Global Nutrition,” J. Nutr. Sci. Vitaminol. (Tokyo)., vol. 65, no. Supplement, pp. S2–S3, Oct. 2019, doi: 10.3177/jnsv.65.S2.

F. Rozi et al., “Indonesian market demand patterns for food commodity sources of carbohydrates in facing the global food crisis,” Heliyon, vol. 9, no. 6, Jun. 2023, doi: 10.1016/j.heliyon.2023.e16809.

Sekretariat Jenderal, “Statistik Iklim, Organisme Pengganggu Tanaman (OPT) dan Dampak Perubahan Iklim (DPI) Tahun 2023 - 2025,” Kementerian Pertanian.

H. Semangun, Penyakit-penyakit tanaman pangan di Indonesia. Gadjah Mada University Press, 2008.

S. S. Gnanamanickam, V. Brindha Priyadarisini, N. N. Narayanan, and S. Kavitha, “An overview of bacterial Blight disease of rice and strategies for its management,” 1999.

C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, p. 60, Dec. 2019, doi: 10.1186/s40537-019-0197-0.

I. Goodfellow et al., “Generative adversarial networks,” Commun. ACM, vol. 63, no. 11, pp. 139–144, Oct. 2020, doi: 10.1145/3422622.

R. A. Saputra, S. Wasyianti, A. Supriyatna, and D. F. Saefudin, “Penerapan Algoritma Convolutional Neural Network Dan Arsitektur MobileNet Pada Aplikasi Deteksi Penyakit Daun Padi,” JURNAL SWABUMI, vol. 9, no. 2, 2021, [Online]. Available: https://archive.ics.uci.edu/ml/datasets/Rice

Q. Zeng, X. Ma, B. Cheng, E. Zhou, and W. Pang, “GANS-based data augmentation for citrus disease severity detection using deep learning,” IEEE Access, vol. 8, pp. 172882–172891, 2020, doi: 10.1109/ACCESS.2020.3025196.

Y. Haruna, S. Qin, and M. J. Mbyamm Kiki, “An Improved Approach to Detection of Rice Leaf Disease with GAN-Based Data Augmentation Pipeline,” Applied Sciences (Switzerland), vol. 13, no. 3, Feb. 2023, doi: 10.3390/app13031346.

T. Agustin, I. A. Saputro, and M. L. Rahmadi, “Optimizing Rice Plant Disease Classification Using Data Augmentation with GANs on Convolutional Neural Networks,” INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi, vol. 9, no. 1, pp. 97–114, Feb. 2025, doi: 10.29407/intensif.v9i1.23834.

T. Karras NVIDIA and S. Laine NVIDIA, “A Style-Based Generator Architecture for Generative Adversarial Networks Timo Aila NVIDIA,” 2019. [Online]. Available: https://github.com/NVlabs/stylegan

T. Karras, M. Aittala, J. Hellsten, S. Laine, J. Lehtinen, and T. Aila, “Training Generative Adversarial Networks with Limited Data,” Oct. 2020, [Online]. Available: http://arxiv.org/abs/2006.06676

Y. Haruna, “Pre-trained StyleGAN2-ADA pytorch Rice Leaf Disease,” Mendeley Data.

T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, Jun. 2006, doi: 10.1016/j.patrec.2005.10.010.

M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, “GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium,” 2017.

M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Sep. 2020.