A LIGHTWEIGHT DEEP LEARNING FRAMEWORK INTEGRATING CBAM AND LION OPTIMIZER FOR SUGARCANE NUTRIENT DEFICIENCY DETECTION
DOI:
https://doi.org/10.29121/shodhkosh.v7.i10s.2026.8075Keywords:
Nutrient Deficiency, Sugarcane, Deep Learning, Mobilenet, Attention MechanismAbstract [English]
Sugarcane is a widely cultivated crop and is grown worldwide. Sugarcane yield is severely affected by the nutrient deficiency problem. Some elements like Nitrogen, Potassium, Phosphorus (macro nutrients), and Boron ( micro nutrients) are essential for the growth of the crop. Early detection of deficiency of these nutrients is essential. In the age of Artificial Intelligence, deep learning techniques are widely used for nutrient deficiency detection. |In this paper a popular deep learning model, MobileNetV3-L, is used to detect the nutrient deficiency in the sugarcane crop. The model is modified by introducing an Attention Module, Convolution Block Attention Module(CBAM) , after the base model to refine the extracted feature, then transfer learning techniques are used to train the model according to our own dataset of 1024 images of sugarcane leaves. Also, we use Lion optimizer for model training. The model gives an accuracy of 93.2% and correctly detected all the above deficiencies.
References
A. Shafique, S. T. Seydi, T. Alipour-Fard, G. Cao and D. Yang, "SSViT-HCD: A Spatial–Spectral Convolutional Vision Transformer for Hyperspectral Change Detection," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 6487-6504, 2023, doi: 10.1109/JSTARS.2023.3251646
Andreas Kamilaris, Francesc X. Prenafeta-Boldú,(2018) Deep learning in agriculture: A survey,Computers and Electronics in Agriculture,Volume 147,2018,Pages 70-90,ISSN 0168-1699,https://doi.org/10.1016/j.compag.2018.02.016.(https://www.sciencedirect.com/science/article/pii/S0168169917308803)
Borja Espejo-Garcia, Ioannis Malounas, Nikos Mylonas, Aikaterini Kasimati, Spyros Fountas, Using EfficientNet and transfer learning for image-based diagnosis of nutrient deficiencies, Computers and Electronics in Agriculture,Volume 196,2022,106868,ISSN 0168-1699,https://doi.org/10.1016/j.compag.2022.106868.(https://www.sciencedirect.com/science/article/pii/S0168169922001855)
Canayaz, M. (2021). C+EffxNet: A novel hybrid approach for COVID-19 diagnosis on CT images based on CBAM and EfficientNet. Chaos, Solitons & Fractals, 151, 111310. https://doi.org/10.1016/j.chaos.2021.111310
Daphal, S.D., Koli, S.M. (2024). Enhanced classification of sugarcane diseases through a modified learning rate policy in deep learning. Traitement du Signal, Vol. 41, No. 1, pp. 441-449. https://doi.org/10.18280/ts.410138
Dubey, A. K., & Dubey, A. (2026). Digitalization in Teaching and Learning: Impact on Student Engagement and Academic Achievement. ShodhAI: Journal of Artificial Intelligence, 3(1), 37–42. https://doi.org/10.29121/shodhai.v3.i1.2026.73
Fu, H., Song, G., & Wang, Y. (2021). Improved YOLOv4 Marine Target Detection Combined with CBAM. Symmetry, 13(4), 623. https://doi.org/10.3390/sym13040623
Guo, C.; Zhou, Q.; Jiao, J.; Li, Q.; Zhu, L. A Modified MobileNetV3 Model Using an Attention Mechanism for Eight-Class Classification of Breast Cancer Pathological Images. Appl. Sci. 2024, 14, 7564. https://doi.org/10.3390/app14177564
https://www.agritech.tnau.ac.in/
https://www.datapandas.org/ranking/sugarcane-production-by-country
https://www.yara.in/crop-nutrition/sugarcane/nutrient-deficiencies-sugarcane/
Kusanur, Vrunda & Chakravarthi, Veena. (2021). Using Transfer Learning for Nutrient Deficiency Prediction and Classification in Tomato Plant. International Journal of Advanced Computer Science and Applications. 12. 10.14569/IJACSA.2021.0121087.
L. Jia et al., "MobileNetV3 With CBAM for Bamboo Stick Counting," in IEEE Access, vol. 10, pp. 53963-53971, 2022, doi: 10.1109/ACCESS.2022.3175818.keywords: {Bamboo;Object detection;Feature extraction;Convolution;Computational modeling;Training;Real-time systems;MobileNetV3;dense bamboo sticks;attention mechanism;border object merger},
Li C, Chen Z, Jing W, Wu X, Zhao Y. A lightweight method for maize seed defects identification based on Convolutional Block Attention Module. Front Plant Sci. 2023 Sep 5;14:1153226. doi: 10.3389/fpls.2023.1153226. PMID: 37731985; PMCID: PMC10508185.
Madhumathi, R., Raghavendar, S., Jegan, B., Naveenganesh, M., Arumuganathan, T. (2023). Transfer Learning-Based Nutrient Deficiency Prediction Model for Sugarcane Crop. In: Fong, S., Dey, N., Joshi, A. (eds) ICT Analysis and Applications. ICT4SD 2023. Lecture Notes in Networks and Systems, vol 782. Springer, Singapore. https://doi.org/10.1007/978-981-99-6568-7_19
S., Vallabhaneni, R. S., Vasireddy, T., & Polavarpu, D. (2022). Deep Ensemble Mobile Application for Recommendation of Fertilizer Based on Nutrient Deficiency in Rice Plants Using Transfer Learning Models. International Journal of Interactive Mobile Technologies (iJIM), 16(16), pp. 100–112. https://doi.org/10.3991/ijim.v16i16.3149
Solomon, Sushil. (2016). Sugarcane Production and Development of Sugar Industry in India. Sugar Tech. 18. 1-15. 10.1007/s12355-016-0494-2.
Srikantamurthy, M.M., Rallabandi, V.P.S., Dudekula, D.B. et al. Classification of benign and malignant subtypes of breast cancer histopathology imaging using hybrid CNN-LSTM based transfer learning. BMC Med Imaging 23, 19 (2023). https://doi.org/10.1186/s12880-023-00964-0 https://www.digitalocean.com/community/tutorials/attention-mechanisms-in-computer-vision-cbam
Taha, M. F., Abdalla, A., ElMasry, G., Gouda, M., Zhou, L., Zhao, N., Liang, N., Niu, Z., Hassanein, A., Al-Rejaie, S., He, Y., & Qiu, Z. (2022). Using Deep Convolutional Neural Network for Image-Based Diagnosis of Nutrient Deficiencies in Plants Grown in Aquaponics. Chemosensors, 10(2), 45. https://doi.org/10.3390/chemosensors10020045
V enkatesh, K., Naik, K.J. Nutrient deficiency identification and yield-loss prediction in leaf images of groundnut crop using transfer learning. SIViP 18, 4553–4568 (2024). https://doi.org/10.1007/s11760-024-03094-4
Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., & Hu, Q. (2019). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. ArXiv. https://arxiv.org/abs/1910.03151
Zhang, Yong & Zhou, Aibo & Zhao, Fengkui & Wu, Haixiao. (2022). A Lightweight Vehicle-Pedestrian Detection Algorithm Based on Attention Mechanism in Traffic Scenarios. Sensors. 22. 8480. 10.3390/s22218480.
Zhu, F., Sun, Y., Zhang, Y., Zhang, W., & Qi, J. (2023). An Improved MobileNetV3 Mushroom Quality Classification Model Using Images with Complex Backgrounds. Agronomy, 13(12), 2924. https://doi.org/10.3390/agronomy13122924
Zou, J., Huss, M., Abid, A. et al. A primer on deep learning in genomics. Nat Genet 51, 12–18 (2019). https://doi.org/10.1038/s41588-018-0295-5
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Debprio Banerjee, Dr. Chetan Vyas
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
