Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206735,
        author = {Vaibhav Narkhede and Priyanka Narkhede},
        title = {Toward Quantum-Enabled Precision Farming: A Hybrid Quantum Machine Learning Approach to Plant Disease Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {2557-2564},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206735},
        abstract = {This Paper provides a comprehensive and novel Hybrid Quantum Machine Learning (HQML) architecture, designed for plant disease detection. It is a significant step forward in precision farming. This framework bridges the advantages of conventional deep learning approaches and the emerging potential of quantum computing in a novel way. The HQML approach tackles the major problems of data scarcity, limited computational resources, and the complexity of nonlinear decision boundaries usually encountered in plant disease identification tasks by combining pretrained CNNs and ViTs for deep feature extraction with quantum encoding techniques and parameterized quantum circuits. The HQML framework is carefully intended to be compatible with Noisy Intermediate-Scale Quantum (NISQ) devices and hence exhibits a pragmatic approach towards near-term quantum hardware implementation. This design consideration guarantees that the model has strong predictive accuracy and computational efficiency, making it suitable for application in resource-constrained scenarios typical of precision agriculture settings. We assessed its performance using multiple metrics, including accuracy, precision, recall, F1 score, Matthews correlation coefficient (MCC), Cohen’s kappa and ROC-AUC, demonstrating its robust classification performance and reliability. Moreover, the computational complexity, convergence speed, inference latency and memory consumption of the proposed framework illustrate the practical feasibility of real-world agricultural applications. Rigorous comparison study benchmarked the HQML model with classical machine learning methods such as Support Vector Machines, Random Forests and XGBoost, and state of the art deep learning architectures such as VGG16, ResNet50, Efficient Net, MobileNetV3 and Vision Transformers. The results frequently indicate the benefits of quantum-augmented learning processes that come with higher accuracy and resource efficiency than solely classical methods. This hybridization builds on the ability of quantum circuits to capture complex non-linear interactions and increase feature separability. This addresses the limitation of traditional deep learning models which require large annotated datasets and considerable processing power. This work paves a practical way to scalable, efficient and accurate plant disease diagnostics by integrating quantum computing with enhanced vision-based feature extraction. The HQML framework can be a game-changer in crop health monitoring, since it can detect illnesses early and correctly, optimize pesticide usage and help in decision-making. These improvements have immediate impact on sustainable agriculture practices and the global food security by increasing crop production and reducing economic losses from plant diseases.},
        keywords = {Hybrid Quantum Machine Learning, detection of plant diseases, precision farming, parameterized quantum circuits, transfer learning, convolutional neural network, NISQ platforms},
        month = {July},
        }