KLASIFIKASI PENYAKIT DAUN PADI BERBASIS CITRA MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DENGAN ARSITEKTUR VGG-16

Fuad Bawazir; Dian Ade Kurnia; Yudhistira  Arie Wijaya; Puji Pramudya Marta

Authors

Fuad Bawazir STMIK IKMI Cirebon, Indonesia
Dian Ade Kurnia STMIK IKMI Cirebon, Indonesia
Yudhistira Arie Wijaya STMIK IKMI Cirebon, Indonesia
Puji Pramudya Marta STMIK IKMI Cirebon, Indonesia

Keywords:

Convolutional Neural Network, VGG-16, Deteksi Penyakit Daun Padi, Augmentasi Citra, Klasifikasi Citra

Abstract

Penyakit daun padi merupakan salah satu faktor utama yang menyebabkan penurunan produktivitas pertanian di Indonesia. Identifikasi penyakit secara dini sangat diperlukan agar tindakan penanganan dapat dilakukan lebih cepat dan akurat. Namun, proses identifikasi manual yang dilakukan oleh petani dan penyuluh sering mengalami kendala karena keterbatasan pengalaman, variasi gejala visual, dan kualitas citra lapangan yang tidak konsisten. Oleh karena itu, penelitian ini berupaya mengembangkan model deteksi penyakit daun padi berbasis citra digital menggunakan arsitektur Convolutional Neural Network (CNN) VGG-16 sebagai solusi cerdas yang mampu mengenali pola penyakit secara otomatis. Permasalahan yang muncul adalah keterbatasan jumlah dataset, variasi pencahayaan, orientasi objek, serta kemiripan gejala antar penyakit seperti Leaf Smut, Brown Spot, dan Bacterial Leaf Blight yang sering menyebabkan kesalahan identifikasi. Untuk mengatasi hal tersebut, penelitian menerapkan preprocessing meliputi resize, normalisasi piksel, dan augmentasi seperti rotasi, zoom, shifting, dan shear agar model lebih tahan terhadap variasi citra. Model VGG-16 yang digunakan memanfaatkan teknik transfer learning dengan penyesuaian ulang lapisan fully connected agar sesuai dengan tiga kelas penyakit. Hasil penelitian menunjukkan bahwa model CNN mampu mencapai akurasi 75%, dengan performa terbaik pada kelas Bacterial Leaf Blight (precision 0.88, recall 0.88) dan tantangan terbesar pada kelas Brown Spot karena variasi pola bercak yang kompleks. Confusion matrix memperkuat bahwa sebagian besar prediksi berada pada kategori benar, meskipun beberapa kesalahan terjadi pada kelas dengan gejala yang saling mirip. Implikasi dari penelitian ini adalah potensi penerapan model CNN sebagai alat bantu diagnosis cepat di sektor pertanian, terutama melalui aplikasi mobile dan sistem monitoring berbasis IoT, sehingga dapat meningkatkan efisiensi dan ketepatan pengambilan keputusan petani dalam mengelola penyakit tanaman

References

Acosta-Prado, J. C., Rojas Rincón, J. S., Mejía Martínez, A. M., & Riveros Tarazona, A. R. (2024). Trends in the Literature About the Adoption of Digital Banking in Emerging Economies: A Bibliometric Analysis. Journal of Risk and Financial Management, 17(12). https://doi.org/10.3390/jrfm17120545

Akhter, R., & Sofi, S. (2022). Precision agriculture using IoT data analytics and machine learning. Journal of King Saud University - Computer and Information Sciences, 34(8), 5602–5618. https://doi.org/10.1016/j.jksuci.2021.05.013

Aljebreen, M., Mengash, H., Kouki, F., & Motwakel, A. (2023). Improved artificial ecosystem optimizer with deep-learning-based insect detection and classification for agricultural sector. Sustainability, 15(20), 14770. https://doi.org/10.3390/su152014770

Cardoso, B., Silva, C., Cósta, J., & Ribeiro, B. (2022). Internet of things meets computer vision to make an intelligent pest monitoring network. Applied Sciences, 12(18), 9397. https://doi.org/10.3390/app12189397

Chen, C., Huang, Y., Li, Y., Chang, C., & Huang, Y. (2020). An AIoT based smart agricultural system for pests detection. IEEE Access, 8, 180750–180761. https://doi.org/10.1109/access.2020.3024891

Chen, C., Huang, Y., Li, Y., Chen, Y., Chang, C., & Huang, Y. (2021). Identification of fruit tree pests with deep learning on embedded drone to achieve accurate pesticide spraying. IEEE Access, 9, 21986–21997. https://doi.org/10.1109/access.2021.3056082

Duarsa, M., Suarna, I., Gede, I., & Wardi, I. (2024a). Tyto alba cultivation in Balinese cultural perspective. International Journal of Life Science and Agriculture Research, 03(02). https://doi.org/10.55677/ijlsar/v03i2y2024-07

Duarsa, M., Suarna, I., Gede, I., & Wardi, I. (2024b). Tyto alba cultivation in Balinese cultural perspective. International Journal of Life Science and Agriculture Research, 03(02). https://doi.org/10.55677/ijlsar/v03i2y2024-07

Gao, D., Sun, Q., Hu, B., & Zhang, S. (2020). A framework for agricultural pest and disease monitoring based on internet-of-things and unmanned aerial vehicles. Sensors, 20(5), 1487. https://doi.org/10.3390/s20051487

Garfansa, M., Iswahyudi, I., & Ekalaturrahmah, Y. (2023a). Introduction of rats pest control using trap barrier system (TBS) in farmer group. Ethos (Jurnal Penelitian Dan Pengabdian), 11(2), 135–142. https://doi.org/10.29313/ethos.v11i2.11125

Garfansa, M., Iswahyudi, I., & Ekalaturrahmah, Y. (2023b). Introduction of rats pest control using trap barrier system (TBS) in farmer group. Ethos (Jurnal Penelitian Dan Pengabdian), 11(2), 135–142. https://doi.org/10.29313/ethos.v11i2.11125

Jiang, J., Liu, Y., Liao, M., Yang, E., Chen, M., Chuang, Y., & Wang, J. (2024). Complementary use of visual and olfactory cues to assess capture of Bactrocera dorsalis (Hendel): Implementation and field verification via an IoT-based automatic monitoring system. Proceedings of the Japan Academy, Series B, 100(1), 68–85. https://doi.org/10.2183/pjab.100.008

Jindal, A., Kansal, M., & Aggarwal, N. (2021). IoT and machine learning based smart surveillance system for pest control in agriculture. Procedia Computer Science, 185, 491–498. https://doi.org/10.1016/j.procs.2021.05.052

Kiobia, D., Mwitta, C., Fue, K., Schmidt, J., Riley, D., & Rains, G. (2023). A review of successes and impeding challenges of IoT-based insect pest detection systems for estimating agroecosystem health and productivity of cotton. Sensors, 23(8), 4127. https://doi.org/10.3390/s23084127

Lian, Y., Wang, A., Peng, S., Jia, J., Zong, L., Yang, X., & Zhou, S. (2022). Optimization of sensors data transmission paths for pest monitoring based on intelligent algorithms. Biosensors, 12(11), 948. https://doi.org/10.3390/bios12110948

Mittal, M., Gupta, V., Aamash, M., & Upadhyay, T. (2024). Machine learning for pest detection and infestation prediction: A comprehensive review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 14(5), e1551. https://doi.org/10.1002/widm.1551

Siregar, H., Priyambodo, S., & Hindayana, D. (2022a). Nisbah kelamin tikus sawah (Rattus argentiventer) pada beberapa fase pertumbuhan tanaman padi di lahan sawah irigasi. Agrovigor Jurnal Agroekoteknologi, 15(2), 75–79. https://doi.org/10.21107/agrovigor.v15i2.11199

Siregar, H., Priyambodo, S., & Hindayana, D. (2022b). Nisbah kelamin tikus sawah (Rattus argentiventer) pada beberapa fase pertumbuhan tanaman padi di lahan sawah irigasi. Agrovigor Jurnal Agroekoteknologi, 15(2), 75–79. https://doi.org/10.21107/agrovigor.v15i2.11199

Sutar, P. P., Kadam, K. V, & Kulkarni, S. (2022). Smart pest monitoring using wireless sensor networks. International Journal of Scientific and Engineering Research, 13(5), 56–61. https://doi.org/10.13140/RG.2.2.15700.42886

Wang, H., Liu, X., & Zhou, Z. (2023). Edge computing based IoT framework for pest detection in agriculture. Sensors, 23(4), 2134. https://doi.org/10.3390/s23042134

Xiang, H., Lan, N., Wang, F., Zhao, B., Wei, H., & Zhang, J. (2021a). Reduced pests, improved grain quality and greater total income: Benefits of intercropping rice with Pontederia cordata. Journal of the Science of Food and Agriculture, 101(14), 5907–5917. https://doi.org/10.1002/jsfa.11243

Xiang, H., Lan, N., Wang, F., Zhao, B., Wei, H., & Zhang, J. (2021b). Reduced pests, improved grain quality and greater total income: Benefits of intercropping rice with Pontederia cordata. Journal of the Science of Food and Agriculture, 101(14), 5907–5917. https://doi.org/10.1002/jsfa.11243

Zhang, Y., Luo, H., & Xu, J. (2023). Deep learning-based detection system for agricultural pest classification. Applied Sciences, 13(7), 3956. https://doi.org/10.3390/app13073956