Abstract

The Fall Armyworm (Spodoptera frugiperda) has emerged as a major constraint on maize cultivation throughout warm-climate agricultural zones. Management practices are most effective during the earliest larval stages, making precise recognition of first- and second-instar caterpillars essential for minimizing crop damage and limiting indiscriminate pesticide application. In response to this requirement, the present work proposes FAWINSTARNet, a computationally efficient deep-learning framework derived from the MobileNetV2 family and tailored for six-category instar discrimination. An initial image repository containing 12,169 samples validated by entomological experts was systematically enlarged to 187,152 images through controlled augmentation to enhance feature variability. A group of ten pretrained convolutional neural networks was evaluated to determine an appropriate trade-off between predictive performance and resource demand. The selected FAWINSTARNet configuration attained an accuracy near 97% and was sufficiently lightweight for execution on mobile hardware, thereby supporting on-site pest surveillance for growers. The study offers a full account of dataset development, experimental procedures, architectural design, and comparative assessment of competing models.

References

• FAO. (2020). Global Action for Fall Armyworm Control: Action Framework 2020. Food and Agriculture Organization of the United Nations.
• Day, R., Abrahams, P., Bateman, M., Beale, T., Clottey, V., Cock, M., Colmenarez, Y., Corniani, N., Early, R., Godwin, J., Gomez, J., Gonzalez-Moreno, P. G., Murphy, S. T., Oppong-Mensah, B., Phiri, N., Pratt, C., Richards, G., Silvestri, S., & Witt, A. (2017). Fall armyworm: Impacts and implications for Africa. Outlooks on Pest Management, 28(5), 196–201. https://doi.org/10.1564/v28_oct_02
• Overton, K., Maino, J. L., Day, R., Umina, P. A., Bett, B., Carnovale, D., Ekesi, S., Meagher, R., & Reynolds, O. L. (2021). Global crop impacts, yield losses and action thresholds for fall armyworm (Spodoptera frugiperda): A review. Crop Protection, 145, Article 105641. https://doi.org/10.1016/j.cropro.2021.105641
• Timilsena, B. P., Niassy, S., Kimathi, E., Abdel-Rahman, E. M., Seidl-Adams, I., Wamalwa, M., Tonnang, H. E. Z., Ekesi, S., Hughes, D. P., Rajotte, E. G., & Subramanian, S. (2022). Potential distribution of fall armyworm in Africa and beyond, considering climate change and irrigation patterns. Scientific Reports, 12, Article 539. https://doi.org/10.1038/s41598-021-04369-3
• Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, Article 1419. https://doi.org/10.3389/fpls.2016.01419
• Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70–90. https://doi.org/10.1016/j.compag.2018.02.016
• Wang, X., Zhang, S., Wang, X., & Xu, C. (2023). Crop pest detection by three-scale convolutional neural network with attention. PLOS ONE, 18(6), e0276456. https://doi.org/10.1371/journal.pone.0276456
• Avotiņš, A., Kviesis, K., Bičāns, J., Alsina, I., & Dubova, L. (2020). Experimental analysis of IoT-based camera SI-NDVI values for tomato plant health monitoring application. Agronomy Research, 18(S1), 5–15.https://doi.org/10.15159/AR.20.087
• Kasinathan, T., Singaraju, D., & Uyyala, S. R. (2021). Insect classification and detection in field crops using modern machine learning techniques. Information Processing in Agriculture, 8(3), 446–457. https://doi.org/10.1016/j.inpa.2020.09.006
• Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4510–4520). https://doi.org/10.1109/CVPR.2018.00474
• Zhang, H., Zhao, S., Song, Y., Ge, S., Liu, D., Yang, X., & Wu, K. (2022). A deep learning and Grad-CAM-based approach for accurate identification of the fall armyworm (Spodoptera frugiperda) in maize fields. Computers and Electronics in Agriculture, 202, Article 107440. https://doi.org/10.1016/j.compag.2022.107440
• Ferentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311–318. https://doi.org/10.1016/j.compag.2018.01.009
• Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 60. https://doi.org/10.1186/s40537-019-0197-0 .