Five-Species Classification of Granivorous Bird Pests in Rice Fields using EfficientNet-B0 Transfer Learning
Abstract
Bird pests significantly threaten rice production in Indonesia, particularly during the generative stage, yet most existing studies focus on general bird detection without distinguishing pest species. This study developed a species-aware classification model to identify five classes (four granivorous pest species and one non-pest class) in rice-field environments. A lightweight convolutional neural network based on EfficientNet-B0 with transfer learning was trained on 2,999 granivorous and 635 non-pest images, which were filtered through duplicate removal, quality screening, and class balancing to produce a curated dataset of 2,112 images. The dataset was split into 70% training and 30% validation sets, and five-fold cross-validation was conducted within the training subset during model development to assess robustness. The model achieved a validation accuracy of 83.38%, with an average cross-validation accuracy of 84.7% ± 1.52% and a macro-average AUC of 0.9724, indicating strong class discrimination. Most misclassifications occurred among morphologically similar Lonchura species rather than random class confusion. An additional 18 in situ field images were used for preliminary external evaluation under natural field conditions, where prediction confidence decreased due to environmental complexity. Overall, the results demonstrate that a lightweight EfficientNet-B0 backbone can effectively distinguish visually similar granivorous pest species from non-pest birds while maintaining computational efficiency suitable for precision agriculture.
Keywords
Full Text:
PDFReferences
E. Andoko and K. A. Adhi, “National Agricultural Development Planning of Indonesia 2025–2029: Economic Transformation Strategies, Inclusive Institutions, and Sustainable Policies Toward Indonesia’s Golden Future 2045 | FFTC Agricultural Policy Platform (FFTC-AP),” 2025. Accessed: Jan. 27, 2026. [Online]. Available: https://ap.fftc.org.tw/article/3821
M. Y. Mohammad, A. S. S. Jahan, V. Sujarajini, and H. M. Haniffa, “Comprehensive review on types of pest attacks in paddy cultivation and botanical control measures,” Crop, Forage and Turfgrass Management, vol. 11, no. 1, pp. 1–13, Jun. 2025, doi: 10.1002/cft2.70026.
W. Suanda, G. A. Rai, I. Made Subrata, K. Y. Suryatini, N. Made, and Y. Maharani, “Keanekaragaman Jenis Hama Tanaman Padi di Area Persawahan Subak Kedua Desa Peguyangan Kangin Kecamatan Denpasar Utara Kota Denpasar sebagai Sumber Pembelajaran Biologi,” Emasains: Jurnal Edukasi Matematika dan Sains, vol. 11, no. 1, pp. 39–47, Mar. 2022, doi: 10.5281/ZENODO.6401689.
A. Ardiyansah, A. Zamzami, and Wulandari, “Rice variety identification system based on drone images to support seed certification process,” Indonesian Journal of Agronomy, vol. 51, no. 1, pp. 79–89, Apr. 2023, doi: 10.24831/ija.v51i1.44111.
Sehabudin, W. Widodo, M. Azizah, and A. A. Oksari, “Kelimpahan Burung Bondol (Genus: Lonchura) di Habitat Persawahan Cilubang Kota Bogor,” in Prosiding Seminar Nasional Sains dan Teknologi Seri 02 Fakultas Sains dan Teknologi, Universitas Terbuka, 2024, pp. 964–971.
I. Pratiwi, S. Priyambodo, and J. B. Hernowo, “Feed Preference, Adaptation, and Role of The Eurasian Tree Sparrows (Passer Montanus L.) in Urban and Rural Environments,” CROPSAVER - Journal of Plant Protection, vol. 5, no. 2, pp. 45–53, Dec. 2022, doi: 10.24198/cropsaver.v5i2.41425.
A. Kurniawan et al., “Pengendalian Hama Burung Pipit Menggunakan Gelombang Ultrasonik Pada Lahan Sawah Musim Kemarau di Tasikmalaya,” Jurnal Pengabdian Cendikia, vol. 2, no. 8, pp. 28–33, 2023, doi: 10.5281/zenodo.10085123.
I. Lucia Kharisma, G. Purnama Insany, A. Rizki Firdaus, and D. Nasrulloh, “Overcoming the Impact of Bird Pests on Rice Yields Using Internet of Things Based YOLO Method,” International Journal of Engineering and Applied Technology, vol. 7, no. 2, pp. 18–32, Nov. 2024, doi: doi.org/10.52005/ijeat.v7i2.111.
N. W. I. Valerience, N. A. Norazlimi, and N. B. M. Abdullah, “Global Perspectives on Pest Bird Research and Management Methods: Implications for Agricultural Areas in Malaysia,” in IOP Conference Series: Earth and Environmental Science, Institute of Physics, 2025, pp. 1–11. doi: 10.1088/1755-1315/1470/1/012012.
M. Fakhrul Hirzi, H. Arahman, and Y. Wibisono, “Smart Ricefield: Development of an Automated Bird Pest Repellent System in Rice Fields Based on IOT and Artificial Intelligence,” Jurnal Ilmiah Multidisiplin Indonesia (JIM-ID), vol. 4, no. 10, pp. 1517–1529, 2025, doi: 10.58471/esaprom.v4i10.
S. Lupica, S. Privitera, A. Trusso Sfrazzetto, E. Cerruto, and G. Manetto, “Toward Modern Pesticide Use Reduction Strategies in Advancing Precision Agriculture: A Bibliometric Review,” Oct. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/agriengineering7100346.
S. Saha, O. D. Kucher, A. O. Utkina, and N. Y. Rebouh, “Precision agriculture for improving crop yield predictions: a literature review,” Jul. 21, 2025, Frontiers Media SA. doi: 10.3389/fagro.2025.1566201.
M. Habil Cahaya Gusti et al., “Diseminasi Teknologi Tepat Guna Berbasis Lingkungan Untuk Mitigasi Hama Burung dan Ketahanan Pertanian di Desa Pakuluran Kabupaten Pandeglang,” Jurnal Pengabdian Ilmu Pendidikan, Sosial, dan Humaniora, vol. 5, no. 1, pp. 229–239, 2025, [Online]. Available: http://journal.unram.ac.id/index.php/darmadiksani
K. Yanel, “Alat Pengusir Hama Burung,” Manutech: Jurnal Teknologi Manufaktur, vol. 15, no. 1, pp. 98–104, 2023, doi: https://doi.org/10.33504/manutech.v15i01.287.
M. Dalal and P. Mittal, “A Systematic Review of Deep Learning-Based Object Detection in Agriculture: Methods, Challenges, and Future Directions,” Computers, Materials and Continua, vol. 84, no. 1, pp. 57–91, 2025, doi: 10.32604/cmc.2025.066056.
W. Yang and X. Qiu, “A Novel Crop Pest Detection Model Based on YOLOv5,” Agriculture (Switzerland), vol. 14, no. 2, pp. 1–23, Feb. 2024, doi: 10.3390/agriculture14020275.
M. I. F. Mohamad Sa’ad, R. Che Ismail, S. Z. M. Naziri, M. N. M. Isa, and A. H. Mohd Shapri, “FPGA-accelerated bird detection algorithm for paddy farmers,” Majlesi Journal of Electrical Engineering, vol. 19, no. 3, pp. 1–11, Sep. 2025, doi: 10.57647/j.mjee.2025.17276.
I. N. Yulita, M. F. R. Rambe, A. Sholahuddin, and A. S. Prabuwono, “A Convolutional Neural Network Algorithm for Pest Detection Using GoogleNet,” AgriEngineering, vol. 5, no. 4, pp. 2366–2380, Dec. 2023, doi: 10.3390/agriengineering5040145.
C. A. Nwonye, K. A. Akpado, T. L. Alumona, O. S. Oguejiofor, and D. O. Amaefule, “Monitoring of Migration of Harmful Sparrow Birds in a Rice Farm Using Convolutional Neural Network (CNN) Model,” UNIZIK Journal of Engineering and Applied Sciences, vol. 3, no. 4, pp. 1144–1162, 2024.
S. Yuliany and A. Nur Rachman, “Implementasi Deep Learning pada Sistem Klasifikasi Hama Tanaman Padi Menggunakan Metode Convolutional Neural Network (CNN),” Jurnal Buana Informatika, vol. 13, no. 1, pp. 54–65, Apr. 2022, doi: doi.org/10.24002/jbi.v13i1.5022.
R. Syahputri, W. Winarto, S. Trisnawati, and T. Taufik, “Android-based Detection of Melon Leaf Diseases Using Convolutional Neural Network and TensorFlow,” vol. 9, no. 1, pp. 48–59, Jul. 2025, doi: 10.31289/jite.v9i1.14542.
S. Raj, S. Garyali, S. Kumar, B. E. Scholar, and S. Shidnal, “Image based Bird Species Identification using Convolutional Neural Network,” International Journal of Engineering Research & Technology (IJERT), vol. 9, no. 6, pp. 346–351, Jun. 2020, [Online]. Available: www.ijert.org
A. Roihan, M. Hasanudin, and E. Sunandar, “Evaluation Methods of Bird Repellent Devices in Optimizing Crop Production in Agriculture,” in Journal of Physics: Conference Series, Institute of Physics Publishing, 2020. doi: 10.1088/1742-6596/1477/3/032012.
M. O. Arowolo, F. T. Fayose, J. A. Ade-Omowaye, A. A. Adekunle, and S. O. Akindele, “Design and Development of an Energy-efficient Audio-based Repellent System for Rice Fields,” International Journal of Emerging Technology and Advanced Engineering, vol. 12, no. 10, pp. 82–94, Oct. 2022, doi: 10.46338/ijetae1022_10.
Y. C. Chen, J. F. Chu, K. W. Hsieh, T. H. Lin, P. Z. Chang, and Y. C. Tsai, “Automatic wild bird repellent system that is based on deep-learning-based wild bird detection and integrated with a laser rotation mechanism,” Sci. Rep., vol. 14, no. 1, pp. 1–15, Dec. 2024, doi: 10.1038/s41598-024-66920-2.
A. Saufi and Suharjito, “White rice stem borer pest detection system using image-based convolution neural network,” in Procedia Computer Science, Elsevier B.V., 2024, pp. 518–527. doi: 10.1016/j.procs.2024.10.278.
C. B. Balingbing et al., “Application of a multi-layer convolutional neural network model to classify major insect pests in stored rice detected by an acoustic device,” Comput. Electron. Agric., vol. 225, pp. 1–13, Oct. 2024, doi: 10.1016/j.compag.2024.109297.
A. Dwicahyo, I. Mufandi, A. R. Nurfadila, M. T. Ardani, and U. Dzilhilmi, “Early Detection of Disease in Chicks Using CNN on Bangkok Chicken Health,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 6, no. 2, pp. 126–141, Jun. 2024, doi: 10.12928/BISTE.V6I2.10245.
K. Eskioğlu and D. Özdemir, “Transforming Poultry Health Management with AI-Powered Disease Detection,” Turkish Journal of Agriculture - Food Science and Technology, vol. 13, no. s3, pp. 4022–4028, Dec. 2025, doi: 10.24925/turjaf.v13is3.4022-4028.8196.
A. Auxtero et al., “RICEGUARD: IoT Noise-Enabled Scarecrow with Image Processing through Machine Learning and SMS Notification for Rice Crop Protection Enhancement,” International Journal of Computing Sciences Research, vol. 9, pp. 3739–3758, 2025, doi: 10.25147/ijcsr.2017.001.1.247.
M. Gärtler, V. Khaydarov, B. Klöpper, and L. Urbas, “The Machine Learning Life Cycle in Chemical Operations – Status and Open Challenges,” Dec. 01, 2021, John Wiley and Sons Inc. doi: 10.1002/cite.202100134.
D. P. Kingma and J. L. Ba, “Adam: A method for stochastic optimization,” in 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, International Conference on Learning Representations, ICLR, 2015, pp. 1–15. Accessed: Mar. 13, 2026. [Online]. Available: https://arxiv.org/pdf/1412.6980
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: a simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, pp. 1929–1958, 2014, Accessed: Mar. 13, 2026. [Online]. Available: https://www.jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf?utm_content=buffer79b43&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer,
M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” in Proceedings of the 36th International Conference on Machine Learning, Long Beach, California: PMLR, Sep. 2019, pp. 6105–6114.
F. Zhuang et al., “A Comprehensive Survey on Transfer Learning,” in Proceedings of the IEEE, Jul. 2020, pp. 43–76.
T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, pp. 861–874, 2006, doi: 10.1016/j.patrec.2005.10.010.
DOI: http://dx.doi.org/10.30829/zero.v10i2.28457
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.