Implementasi Transfer Learning dengan Arsitektur Mo-bileNetV2 untuk Klasifikasi Penyakit pada Daun Padi

Alek Wijaya; Andre Satriawan; M. Soekarno Putra; Muhammad Nasir

doi:10.55606/jitek.v5i3.8389

Authors

Alek Wijaya Universitas Bina Darma
Andre Satriawan Universitas Bina Darma
M. Soekarno Putra Universitas Bina Darma
Muhammad Nasir Universitas Bina Darma

DOI:

https://doi.org/10.55606/jitek.v5i3.8389

Keywords:

Transfer Learning, MobileNetV2, Rice Leaf Disease, Classification, Streamlit

Abstract

Rice is a strategic commodity in Indonesia, yet its productivity is often threatened by leaf diseases such as Bacterial Leaf Blight, Brown Spot, Narrow Brown Spot, and Tungro. Conventional identification conducted by farmers is subjective and may delay proper treatment. This study implements transfer learning using the MobileNetV2 architecture for rice leaf disease classification. The dataset was collected directly from rice fields in OKU Timur, South Sumatra, consisting of five classes (Bacterial Leaf Blight, Brown Spot, Healthy, Narrow Brown Spot, and Tungro), each containing 300 images except Narrow Brown Spot, which was balanced through light augmentation. All images underwent cropping, resizing to 224×224 pixels, and normalization before being split into training, validation, and testing sets. The proposed model achieved 99.11% validation accuracy and 100% testing accuracy, with near-perfect precision, recall, and f1-score. The model was then deployed into a user-friendly web application using Streamlit, enabling farmers to upload rice leaf images for instant classification and recommended treatments. These findings demonstrate that MobileNetV2 with transfer learning provides accurate early detection of rice leaf diseases and supports better decision-making in rice cultivation.

References

[1] A. Hasibuan, S. P. Nasution, F. A. Yani, H. A. Hasibuan, and N. Firzah, “Strategi Peningkatan Usaha Tani Padi Sawah Untuk Meningkatkan Perekonomian Masyarakat Desa,” ABDIKAN: Jurnal Pengabdian Masyarakat Bidang Sains dan Teknologi, vol. 1, no. 4, pp. 477–490, Nov. 2022, doi: 10.55123/abdikan.v1i4.1095.

[2] R. Laraswati, U. Kulsim, and E. P. Ramdan, “Efikasi Ekstrak Sirih, Rimpang Lengkuas dan Kunyit terhadap Penekanan Pertumbuhan Xanthomonas oryzae,” 2021.

[3] Y. F. Rachman, P. Susanti, A. B. R. P. A. Putra, and N. I. Rahmawati, “Sistem Informasi Deteksi Penyakit Pada Tanaman Padi Menggunakan Metode CNN,” Decode: Jurnal Pendidikan Teknologi Informasi, vol. 4, no. 3, pp. 1193–1204, Nov. 2024, doi: 10.51454/decode.v4i3.846.

[4] J. J. Hidayat, C. Setyowati, and A. P. Werdana, “Analisis Penyakit pada Daun Padi Menggunakan VGG-16 Transfer Learning dan Teknik Segmentasi K-Mean,” Jurnal Media Infotama, vol. 21, no. 1, 2025. [Online]. Available: www.kaggle.com

[5] I. F. Annur, J. Umami, M. N. Annafii, N. Trisnaningrum, and O. V. Putra, “Klasifikasi Tingkat Keparahan Penyakit Leafblast Tanaman Padi Menggunakan MobileNetV2,” Fountain of Informatics Journal, vol. 8, no. 1, pp. 7–14, May 2023, doi: 10.21111/fij.v8i1.9419.

[6] O. V. Putra, M. Z. Mustaqim, D. Muriatmoko, J. Teknik Informatika, and F. Sains dan Teknologi, “Transfer Learning untuk Klasifikasi Penyakit dan Hama Padi Menggunakan MobileNetV2,” 2023.

[7] D. Husen, “Evaluasi Teknik Augmentasi Data Untuk Klasifikasi Tumor Otak Menggunakan CNN Pada Citra MRI,” Husem, 2021.

[8] Y. F. Rachman, P. Susanti, A. B. R. P. A. Putra, and N. I. Rahmawati, “Sistem Informasi Deteksi Penyakit Pada Tanaman Padi Menggunakan Metode CNN,” Decode, vol. 4, no. 3, pp. 1193–1204, Nov. 2024, doi: 10.51454/decode.v4i3.846.

[9] J. J. Hidayat, C. Setyowati, and A. P. Werdana, “Analisis Penyakit pada Daun Padi Menggunakan VGG-16 Transfer Learning dan Teknik Segmentasi K-Mean,” Jurnal Media Infotama, 2025. [Online]. Available: www.kaggle.com

[10] I. F. Annur, J. Umami, M. N. Annafii, N. Trisnaningrum, and O. V. Putra, “Klasifikasi Tingkat Keparahan Penyakit Leafblast Tanaman Padi Menggunakan MobileNetV2,” Fountain of Informatics Journal, vol. 8, no. 1, pp. 7–14, May 2023, doi: 10.21111/fij.v8i1.9419.

[11] H. Ning, S. Liu, Q. Zhu, and T. Zhou, “Convolutional neural network in rice disease recognition: accuracy, speed and lightweight,” Frontiers in Plant Science, 2023, doi: 10.3389/fpls.2023.1269371.

[12] G. Latif et al., “Deep Learning Utilization in Agriculture: Detection of Rice Plant Diseases Using an Improved CNN Model,” Plants, vol. 11, no. 17, Sep. 2022, doi: 10.3390/plants11172230.

[13] A. R. Hermanto, A. Aziz, and S. Sudianto, “Perbandingan Arsitektur MobileNetV2 dan ResNet50 untuk Klasifikasi Jenis Buah Kurma,” Jurnal Sistem dan Teknologi Informasi, vol. 12, no. 4, 2024, doi: 10.26418/justin.v12i4.80358.

[14] A. Jalil, A. Homaidi, and Z. Fatah, “Implementasi Algoritma SVM Untuk Klasifikasi Status Stunting Pada Balita,” G-Tech: Jurnal Teknologi Terapan, vol. 8, no. 3, pp. 2070–2079, Jul. 2024, doi: 10.33379/gtech.v8i3.4811.

[15] R. Laraswati, E. P. Ramdan, U. Kulsum, and B. B. POPT, “Identifikasi Penyebab Penyakit Hawar Daun Bakteri Pada Kombinasi Pola Tanam SRI dan Jajar Legowo,” AGROPROSS, 2021, doi: 10.25047/agropross.2021.234.

[16] A. Walascha et al., “Inventarisasi Jenis Penyakit yang Menyerang Daun Tanaman Padi,” Prosiding SEMNAS BIO, 2021.

[17] W. Ratna Rohaeni and D. Yuliani, “Keragaman Morfologi Daun Padi Lokal Indonesia dan Korelasinya dengan Ketahanan Penyakit Hawar Daun Bakteri,” JIPI, vol. 24, no. 3, pp. 258–266, 2019, doi: 10.18343/jipi.24.3.258.

[18] R. A. W. Atmaja, S. J. Santosa, and S. Siswadi, “Kajian Pupuk Kandang terhadap Intensitas Penyakit Bercak Coklat Sempit,” Jurnal Inovasi Pertanian, vol. 22, no. 1, 2020.

[19] M. Sutrawati, Y. Sariasih, P. Priyatiningsih, and F. T. Ladja, “Deteksi Virus Tungro Pada Padi di Bengkulu,” Jurnal Ilmu-Ilmu Pertanian Indonesia, vol. 21, no. 2, pp. 99–102, Dec. 2019, doi: 10.31186/jipi.21.2.99-102.

[20] I. R. Huriah, A. I. S. Widianingrum, and U. Muhammadiyah Riau, “Optimasi Augmentasi Data Berbasis Synonym Replacement,” Komputa, vol. 14, no. 1, 2025, doi: 10.34010/komputa.v14i1.

[21] H. Zhou, J. Deng, D. Cai, X. Lv, and B. M. Wu, “Effects of Image Dataset Configuration on the Accuracy of Rice Disease Recognition Based on CNN,” Frontiers in Plant Science, vol. 13, Jul. 2022, doi: 10.3389/fpls.2022.910878.

[22] R. R. Sani, Y. A. Pratiwi, S. Winarno, E. D. Udayanti, and F. A. Zami, “Analisis Perbandingan Algoritma NBC dan SVM untuk Klasifikasi Hoax,” 2022.

[23] R. Mardianto, S. Quinevera, and S. Rochimah, “Perbandingan Metode RF, CNN, dan SVM Untuk Klasifikasi Jenis Mangga,” JACOST, vol. 5, no. 1, pp. 63–71, May 2024, doi: 10.52158/jacost.v5i1.742.

[24] S. Dewi et al., “Analisis Sentimen Aplikasi WhatsApp Berdasarkan Ulasan di PlayStore,” AJST, vol. 2, no. 2, 2024. [Online]. Available: http://jurnal.ardenjaya.com/index.php/ajst

[25] J. Digital and T. Informasi, “Prediksi Penyakit Jantung Berbasis Machine Learning Menggunakan Metode K-NN,” Jurnal Digital, vol. 7, no. 2, pp. 14–20, 2024, doi: 10.32502/digital.v7i2.9429.

[26] M. Julkarnain and M. Yustiardin, “Penerapan Algoritma Naive Bayes dalam Memprediksi Lulus Tepat Waktu Mahasiswa,” Digital Transformation Technology, vol. 4, no. 2, pp. 848–858, Dec. 2024, doi: 10.47709/digitech.v4i2.4963.