AI-Based Plant Pest Detection and Treatment Recommendation Using YOLOv8

The Plant Pest Detection system is powered by the YOLOv8 object detection model, which enables detection and classification of a few pest species from images of crops uploaded at the time of analysis. The proposed system can reduce the identification time and labor as well as improve the identification accuracy compared with manually inspecting and expertly identifying the pests. Compared with traditional image classification methods, bounding box detection can be used to precisely detect pests in the image and is more effective.   To conclude, the system proposed is fruitful at achieving the overall aim of the research, such as actual detection of pests, smart recommendation of treatment, and significant presentation of direction in pest management. It can help minimize losses, boost productivity, decrease the amount of pesticides that are used, and assist farmers in using more efficient and sustainable farming methods. Overall, the study shows the promise of AI in solving real-world challenges in agriculture and in advancing the development of smart farming.

[1]    A. Fuentes, S. Yoon, S. C. Kim, and D. S. Park, “A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition,” Sensors, vol. 17, no. 9, Art. no. 2022, 2017, doi: 10.3390/s17092022. [2]    X. Wu, C. Zhan, Y.-K. Lai, M.-M. Cheng, and J. Yang, “IP102: A large-scale benchmark dataset for insect pest recognition,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 8787–8796, doi: 10.1109/CVPR.2019.00899. [3]    K. Thenmozhi and U. S. Reddy, “Crop pest classification based on deep convolutional neural network and transfer learning,” Computers and Electronics in Agriculture, vol. 164, Art. no. 104906, 2019, doi: 10.1016/j.compag.2019.104906. [4]    X. Wang, S. Zhang, X. Wang, and C. Xu, “Crop pest detection by three-scale convolutional neural network with attention,” PLOS ONE, vol. 18, no. 6, Art. no. e0276456, 2023, doi: 10.1371/journal.pone.0276456. [5]    C. Yang, Y. Wang, L. Yun, H. Wang, Y. Han, and Z. Chen, “IP-YOLOv8: A multi-scale pest detection algorithm for field-scale applications,” Horticulturae, vol. 11, no. 9, Art. no. 1109, 2025, doi: 10.3390/horticulturae11091109. [6]    J. Wei, H. Gong, S. Li, M. You, H. Zhu, L. Ni, L. Luo, M. Chen, H. Chao, and Y. Sun, “Improving the accuracy of agricultural pest identification: Application of AEC-YOLOv8n to large-scale pest datasets,” Agronomy, vol. 14, no. 8, Art. no. 1640, 2024, doi: 10.3390/agronomy14081640. [7]    S.-Y. Zhou and C.-Y. Su, “Efficient convolutional neural network for pest recognition—ExquisiteNet,” in Proc. 2nd IEEE Eurasia Conf. IoT, Commun. Eng. (ECICE), 2020, pp. 216–219. [8]    J. White, C. Agrawal, A. Ojha, A. Agnihotri, M. Sharma, and J. Doshi, “BOLLWM: A real-world dataset for bollworm pest monitoring from cotton fields in India,” in Proc. PML4DC Workshop at ICLR, 2023. [9]    S. Chiranjeevi, M. Saadati, Z. K. Deng, J. Koushik, T. Z. Jubery, D. S. Mueller, M. E. O. Neal, N. C. Merchant, A.   Singh, A. K. Singh, S. Sarkar, A. Singh, and B. Ganapathysubramanian, “Deep learning powered real-time identification of insects using citizen science data,” arXiv preprint arXiv:2306.02507, 2023, doi: 10.48550/arXiv.2306.02507. [10]   M. Shoaib, A. Sadeghi-Niaraki, F. Ali, I. Hussain, and S. K. Shah, “Leveraging deep learning for plant disease and pest detection: A comprehensive review and future directions,” Frontiers in Plant Science, vol. 16, 2025, Art. no. 1538163, doi: 10.3389/fpls.2025.1538163.