Legume Research

Legume Research cover
Volume 49 · Issue 4 · 2026/04/06

Evaluation of a Convolutional Neural Network-based Model for Accurate Detection and Multi-class Classification of Economically Significant Soybean Pests using RGB Image Data

Pragalbh Sharma
Ashish Kulkarni
Shalini Sharma
Pooja Kulkarni
Shweta Karsauliya
Sandeep Dongre
354 Views

Submitted

2025/12/08

First Online

2026/04/06

doi

10.18805/LR-5622

Cite article - Pragalbh Sharma, Ashish Kulkarni, Shalini Sharma, Pooja Kulkarni, Shweta Karsauliya, Sandeep Dongre. (2026). Evaluation of a Convolutional Neural Network-based Model for Accurate Detection and Multi-class Classification of Economically Significant Soybean Pests using RGB Image Data. Legume Research. 49(4): 692–700. doi: 10.18805/LR-5622

Abstract

Background: Soybean ( Glycine max ) is a vital legume crop cultivated worldwide for its high protein and oil content. However, its productivity is significantly affected by various insect pests that damage leaves, stems and pods during different growth stages. Pests like aphids, armyworms and bollworms can cause substantial yield losses if not detected and controlled promptly. Manual pest monitoring through field scouting remains the dominant practice but is labour-intensive, inconsistent and prone to human error, particularly in large-scale farming systems. The integration of artificial intelligence, particularly deep learning, offers a scalable solution for automating pest detection.

Methods: This study presents a convolutional neural network (CNN) model designed to detect and classify seven major insect pests commonly found in soybean crops. A dataset consisting of 2,450 RGB images was collected from online resources. The images were preprocessed, augmented and split into training, validation and test sets. The CNN was built using six convolutional layers with ReLU activations, followed by max-pooling layers, a fully connected dense layer and a softmax output layer for classification. The model was trained for 100 epochs using the Adam optimizer and sparse categorical cross-entropy loss.

Result: The final model achieved an overall accuracy of 96.88% on the test set. Class-wise evaluation showed high classification matrices across all categories. ROC-AUC values reached 1.00 for all pest classes, indicating excellent classification performance. Precision-recall curves also showed high average precision scores, confirming the model’s reliability. These results demonstrate the model’s potential for practical application in real-time pest monitoring systems used in precision agriculture.

References

  1. Agarwal, A., Vats, S., Agarwal, R., Ratra, A., Sharma, V. and Jain, A. (2023). EfficientNetB3 for Automated Pest Detection in Agriculture. In Proceedings of the 2023 10 th International Conference on Computing for Sustainable Global Development (INDIACom). IEEE. (pp. 1408-1413). AlZubi, A.A. (2023). Artificial Intelligence and its application in the prediction and diagnosis of animal diseases: A review. Indian Journal of Animal Research . 57(10): 1265-1271. doi: 10.18805/IJAR.BF-1684 . Bagga, T., Ansari, A.H., Akhter, S., Mittal, A. and Mittal, A. (2024). Understanding indian consumers’ propensity to purchase electric vehicles: An analysis of determining factors in environmentally sustainable transportation. International Journal of Environmental Sciences . 10(1): 1-13. Bhoi, M. and Sharma, P. (2025). An advanced LSTM framework for pest detection and classification in agricultural settings. SHS Web of Conferences . 216: 01032. https:/ /doi.org/10.1051/shsconf/202521601032. Cho, O.H. (2024). An evaluation of various machine learning approaches for detecting leaf diseases in agriculture. Legume Research . 47(4): 619-627. doi: 10.18805/LRF-787 . De Melo L.B.P., De Araújo, B.B.L., Hirose, E. and Borges, D.L. (2024). A lightweight and enhanced model for detecting the neotropical brown stink bug, Euschistus heros (Hemiptera: Pentatomidae) based on YOLOv8 for soybean fields. Ecological Informatics . 80: 102543. https://doi.org/10.1016/j.ecoinf.2024.102543. Faye, B., Azzag, H., Lebbah, M. and Feng, F. (2024). Context normalization: A new approach for the stability and improvement of neural network performance. Data and Knowledge Engineering . 155: 102371. https://doi.org/ 10.1016/j.datak.2024.102371. FAOSTAT. (2023). Soybeans: Yields by Country (tonnes per hectare), 2023. Food and Agriculture Organization of the United Nations. https://www.fao.org/faostat/en/ #data/QC. Gaur, N. and Mogalapu, S. (2018). Pests of Soybean. In Springer eBooks (pp. 137-162). https://doi.org/10.1007/978-981-10-8687-8_6. Gui, J., Xu, H. and Fei, J. (2023). Non-destructive detection of soybean pest based on hyperspectral image and attention-resnet meta-learning model. Sensors . 23(2): 678. https://doi.org/10.3390/s23020678. Hai, N.T. and Duong, N.T. (2024). An improved environmental management model for assuring energy and economic prosperity. Acta Innovations . 52: 9-18. https://doi.org/ 10.62441/ActaInnovations.52.2. Heinrichs, E.A. and Muniappan, R. (2019). Integrated pest management for tropical crops: Soybeans. CABI Reviews . 1-44. https://doi.org/10.1079/pavsnnr201813055. Huang, M., Wan, X., Zhang, M. and Zhu, Q. (2012). Detection of insect-damaged vegetable soybeans using hyperspectral transmittance image. Journal of Food Engineering . 116(1): 45-49. https://doi.org/10.1016/j.jfoodeng.2012.11.014. ISWS. (2024). Addressing yield gaps in Indian soybean cultivation through integrated weed and pest management. Indian Journal of Weed Science . 56(4): 417-425. Kasinathan, T. and Uyyala, S.R. (2021). Machine learning ensemble with image processing for pest identification and classification in field crops. Neural Computing and Applications . 33(13): 7491-7504. https://doi.org/10.1007/s00521-020-05497-z. Ma, Y., Huang, M., Yang, B. and Zhu, Q. (2014). Automatic threshold method and optimal wavelength selection for insect- damaged vegetable soybean detection using hyperspectral images. Computers and Electronics in Agriculture . 106: 102-110. https://doi.org/10.1016/j.compag.2014.05.014. Maltare, N.N., Sharma, D. and Patel, S. (2023). An exploration and prediction of rainfall and groundwater level for the District of Banaskantha, Gujarat, India. International Journal of Environmental Sciences . 9(1): 1-17. Nargund, R., Bhatia, V.S., Sinha, N.K., Mohanty, M., Jayaraman, S., Dang, Y.P., Nataraj, V., Drewry, D. and Dalal, R.C. (2024). Assessing soybean yield potential and yield gap in different agroecological regions of India using the DSSAT model. Agronomy . 14(9): 1929. https://doi.org/ 10.3390/agronomy14091929. Natukunda, M.I. and MacIntosh, G.C. (2020). The resistant soybean- aphis glycines interaction: Current knowledge and prospects. Frontiers in Plant Science . 11. https://doi.org/10.3389/fpls.2020.01223. Park, Y., Choi, S. H., Kwon, Y., Kwon, S., Kang, Y.J. and Jun, T. (2023). Detection of soybean insect pest and a forecasting platform using deep learning with unmanned ground vehicles. Agronomy . 13(2): 477. https://doi.org/10.3390/ agronomy13020477. Sahin, Y.S., Gençer, N.S. and Şahin, H. (2025). Integrating AI detection and language models for real-time pest management in Tomato cultivation. Frontiers in Plant Science. 15. https://doi.org/10.3389/fpls.2024.1468676. Shah, D., Gupta, R., Patel, K., Jariwala, D. and Kanani, J. (2022). Deep Learning Based Pest Classification in Soybean Crop using Residual Network 50. In: Proceedings of the 2022 IEEE 2 nd International Symposium on Sustainable Energy, Signal Processing and Cyber Security (iSSSC). IEEE. (pp./1-5). https://doi.org/10.1109/iSSSC56467.2022.10051424. Shinde, S. and Attar, V. (2024). MH-SoyaHealthVision: An Indian UAV and leaf image dataset for integrated crop health assessment (Version 1) [Data set]. Mendeley Data. https://doi.org/10.17632/hkbgh5s3b7.1. Suárez-Paniagua, V. and Segura-Bedmar, I. (2018). Evaluation of pooling operations in convolutional architectures for drug-drug interaction extraction. BMC Bioinformatics. 19(S8). https://doi.org/10.1186/s12859-018-2195-1. Tailanián, M., Castiglioni, E., Musé, P., Flores, G.F., Lema, G., Mastrángelo, P., Almansa, M., Liñares, I.F. and Liñares, G.F. (2015). Early pest detection in soy plantations from hyperspectral measurements: A case study for caterpillar detection. Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE . 9637: 96372I. https://doi.org/10.1117/12.2195083. Tang, Z., Lu, J., Chen, Z., Qi, F. and Zhang, L. (2023). Improved pest-YOLO: Real-time pest detection based on efficient channel attention mechanism and transformer encoder. Ecological Informatics . 78: 102340. https://doi.org/ 10.1016/j.ecoinf.2023.102340. Tetila, E.C., Machado, B.B., Astolfi, G., De Souza, B.N.A., Amorim, W.P., Roel, A.R. and Pistori, H. (2020). Detection and classification of soybean pests using deep learning with UAV images. Computers and Electronics in Agriculture . 179: 105836. https://doi.org/10.1016/j.compag.2020.105836. Teuwen, J. and Moriakov, N. (2019). Convolutional Neural Networks. In Elsevier eBooks (pp. 481–501). https://doi.org/10.1016/ b978-0-12-816176-0.00025-9. Venkatasaichandrakanth, P. and Iyapparaja, M. (2024). A survey on pest detection and classification in field crops using artificial intelligence techniques. International Journal of Intelligent Robotics and Applications. 8(3): 709-734. https://doi.org/10.1007/s41315-024-00347-w. Xiang, Q., Huang, X., Huang, Z., Chen, X., Cheng, J. and Tang, X. (2023). Yolo-pest: An insect pest object detection algorithm via CAC3 module. Sensors . 23(6): 3221. https://doi.org/10.3390/s23063221. Zhang, Y. and Lv, C. (2024). TinySegformer: A lightweight visual segmentation model for real-time agricultural pest detection. Computers and Electronics in Agriculture . 218: 108740. https://doi.org/10.1016/j.compag.2024.108740.
EDITORIAL BOARD

Guided by Experienced Academic Leadership

Distinguished scholars and subject experts committed to editorial excellence, scientific integrity and rigorous peer review.

View Full Board
Kadambot Siddique
Chief Editor

Kadambot Siddique

DirectorThe UWA Institute of Agriculture, The University of Western Australia, AUSTRALIA

Pei Xu
Associate chief editor

Pei Xu

DeanChina Jiliang University, CHINA

Satpal Singh Bisht
Editor

Satpal Singh Bisht

Vice ChancellorS.S.J.University Almora, Uttarakhand, INDIA

H.K. Dikshit
Editor

H.K. Dikshit

Principal Scientist Indian Agricultural Research Institute, New Delhi, INDIA