Deep Learning with Quantum Computing for Coconut Disease and Nutrient Deficiency Detection.

Author

Uttaravilli Indraja, Reddi Lokesh, Padilapu Bharadwaja, Naidu Jayavardhan, Dr. K. Srividya

Abstract

 Crops can be impaired in quality and yield due to coconut diseases, pest damage and nutrient deficiencies. These conditions can be difficult to diagnose, especially at an early stage, as their symptoms often overlap and/or expert help is not available to support the diagnosis. In this paper, a hybrid architecture between CNN and Variational Quantum Circuit (VQC) is proposed for the classification of healthy and unhealthy images of coconut. A classical CNN is used to obtain four numerical features from the images of a coconut, which are then processed by a four-qubit variational quantum circuit. This quantum circuit's output is fed into a classical prediction head for final classification. The framework also includes recommended treatment and preventive measures and a suggested process for severity determination and treatment. The results of the experimental evaluation show that the hybrid model outperformed the classical CNN baseline model in terms of aggregate classification accuracy on the dataset used. The results indicated that the approach proposed may be useful to the development of intelligent image-based coconut health assessment systems. More detailed measurements using class-wise metrics and experiments should be conducted to determine its reliability. 

Keywords

Real-Time Coconut Disease and Nutrient Deficiency Detection, Deep Learning, Convolutional Neural Networks (CNN), Simple Quantum Computing, Precision Agriculture.

Full Text:

Download Paper PDF

References

[1] D. Devarajan, R. Allafi, M. Obayya, and N. Nemri, “AI based real time disease diagnosis in plants using deep learning driven CNNs,” Scientific Reports, vol. 16, art. no. 4587, 2026.

doi: 10.1038/s41598-025-34681-1.

[2] S. Murugavalli and R. Gopi, “Plant leaf disease detection using vision transformers for precision agriculture,” Scientific Reports, vol. 15, art. no. 22361, 2025. doi: 10.1038/s41598-025-05102-0.

[3] C. Pal, S. Karmakar, I. Mukherjee, and P. P. Chakrabarti, “A lightweight and explainable CNN model for empowering plant disease diagnosis,” Scientific Reports, vol. 15, art. no. 30720, 2025. doi: 10.1038/s41598-025-94083-1.

[4] K. Sahu, S. Tiwari, M. K. Singh, J. Pahareeya, H. K. Shakya, G. Kumar, and S. Selvarajan, “Plant disease detection using a hybrid dilated CNN with attention mechanisms and optimized Mask R-CNN segmentation,” Scientific Reports, vol. 15, art. no. 42008, 2025. doi: 10.1038/s41598-025-26192-w.

[5] Z. Zeng, T. Mahmood, Y. Wang, A. Rehman, and M. A. Mujahid, “AI-driven smart agriculture using hybrid Transformer-CNN for real-time disease detection in sustainable farming,” Scientific Reports, vol. 15, art. no. 25408, 2025. doi: 10.1038/s41598-025-10537-6.

[6] T. Zhang, D. Wang, and W. Chen, “Multiscale CNN-state space model with feature fusion for crop disease detection from UAV imagery,” Frontiers in Plant Science, vol. 16, art. no. 1733727, 2025. doi: 10.3389/fpls.2025.1733727.

[7] Z. Arshad, A. Javed, and A. K. J. Saudagar, “ConvGeM-next: A deep learning framework for plant disease detection,” Frontiers in Plant Science, vol. 17, art. no. 1763739, 2026. doi: 10.3389/fpls.2026.1763739.

[8] M. Saleema, J. E. Martis, and S. Abdulhayan, “Deep learning model for automated detection and classification of coconut trees aliments,” International Journal of Applied Mathematics, vol. 38, no. 10s, 2025. doi: 10.12732/ijam.v38i10s.1014.

[9] P. Goyal, J. Gill, R. Goyal, M. Sharma, and K. Sharma, “Deep learning-based citrus plant disease classification using a computationally efficient CNN model,” Scientific Reports, vol. 16, art. no. 19316, 2026. doi: 10.1038/s41598-026-50684-y.

[10] J. Hoffmann, C. Mai, and R. Buettner, “A novel deep-learning approach for robust identification of

plant diseases,” PLOS ONE, vol. 21, art. no. e0353374, 2026. doi: 10.1371/journal.pone.0353374.

[11] A. Ullah, S. Hussain, Q. Hou, D. Fang, and L. Deng, “EDISP: A hybrid CNN-ViT framework for robust maize leaf disease detection and classification,” Frontiers in Plant Science, vol. 17, art. no. 1873194, 2026. doi: 10.3389/fpls.2026.1873194.

[12] S. K. Manoharan, R. K. Megalingam, G. A., G. Jogesh, K. Aryan, and A. R. Kunnambath, “AI

based early identification and severity detection of nutrient deficiencies in coconut trees,” Smart Agricultural Technology, vol. 9, art. no. 100575, 2024. doi: 10.1016/j.atech.2024.100575.

[13] S. Muthusamy and S. P. Ramu, “A neural architecture search optimized lightweight attention ensemble model for nutrient deficiency and severity assessment in diverse crop leaves,” Scientific Reports, vol. 15, art. no. 37390, 2025. doi: 10.1038/s41598-025-20124-4.

[14] S. Kulkarni, V. Shashidhar, P. D. Shenoy, and V. K. R., “A time-efficient hybrid QFT-QCNN framework for high-accuracy coffee leaf disease detection,” International Journal of Applied Mathematics, vol. 38, no. 10s, 2025. doi: 10.12732/ijam.v38i10s.1030.

[15] A. S. Al-Shamayleh and R. W. Ibrahim, “Grapevine disease detection using (q,τ)-nabla calculus quantum deformation with deep learning features,” MethodsX, vol. 15, art. no. 103619, 2025. doi: 10.1016/j.mex.2025.103619.

 

Share your valuable work from Social Media Buttons