Plant Disease Monitoring System Using Convolutional Neural Networks and Flask Web Framework

Abstract

Agriculture continues to face major challenges due to the widespread impact of plant diseases that reduce both crop yield and quality. Early detection and accurate diagnosis of these diseases are essential for preventing large-scale losses and supporting sustainable farming. This research presents a Plant Disease Monitoring System developed using a Convolutional Neural Network (CNN) integrated with the Flask web framework. The system enables users—particularly farmers and agricultural practitioners—to upload images of plant leaves and receive instant feedback on the presence and type of disease. The CNN model was trained on the publicly available PlantVillage dataset, containing a wide range of healthy and diseased leaf images. The application processes the uploaded image, classifies the disease, and displays the prediction along with possible remedies and preventive measures. This web-based solution is lightweight, user-friendly, and accessible from any device with an internet connection. Experimental evaluation demonstrated high accuracy and reliable performance in detecting common plant diseases under controlled conditions. By minimizing the need for expert consultation and reducing diagnostic time, the proposed system contributes toward precision agriculture, improved crop health management, and increased farmer awareness. Future enhancements may include real-time field integration using IoT sensors and expanding the model to support a broader variety of crops and environmental conditions.

Introduction

Plant diseases pose a major threat to global agriculture by reducing crop yield and quality, while traditional diagnostic methods are slow, costly, and often inaccessible. Advances in artificial intelligence—especially computer vision and deep learning—have enabled automated plant disease detection using leaf images. Convolutional neural networks (CNNs) are particularly effective because they automatically learn complex visual patterns linked to diseases, offering faster and more accurate identification than manual methods. However, current AI systems face challenges such as limited dataset diversity, difficulty handling real-world variability, and poor integration into practical farming workflows.

To address these limitations, the work introduces a web-based Plant Disease Monitoring System. It employs a CNN trained on the PlantVillage dataset and deploys the model through a Flask-powered web interface, allowing users to upload leaf images and receive instant disease predictions and treatment suggestions. This approach aims to make AI-driven plant diagnostics accessible, scalable, and usable in real farming environments.

The main contributions include developing a CNN classifier, deploying it via a lightweight Flask application, and validating its performance while discussing future improvements like IoT integration and edge deployment. The text also explains the key concepts behind AI and deep learning in agriculture, the role of CNNs in image-based disease detection, and the importance of web frameworks like Flask for practical deployment. By integrating deep learning with web technologies, the system supports smart agriculture and empowers farmers with timely, data-driven crop health insights.

Conclusion

This study presented a practical and accessible Plant Disease Monitoring System that integrates a convolutional neural network (CNN) with a Flask web framework to deliver real-time, web-based plant disease identification. By leveraging the publicly available PlantVillage dataset and optimizing the CNN for classification efficiency, the proposed system demonstrates strong diagnostic performance and a lightweight architecture suitable for online deployment. Unlike several prior works [9]–[12], which focus primarily on model development in isolated laboratory settings, this research emphasizes usability, scalability, and accessibility—critical components for real-world agricultural implementation. The system contributes to the growing field of precision agriculture by reducing farmers’ dependence on expert consultation and enabling faster, data-driven decisions for disease control. The web-based interface ensures platform independence, allowing users to upload leaf images and receive instant diagnostic feedback. This fusion of deep-learning intelligence and web technology bridges the gap between advanced AI research and field-level agricultural practice. Looking ahead, several promising directions can further enhance the system’s capabilities. First, expanding the training dataset with diverse, field-captured images from multiple crops will strengthen generalization across environmental conditions. Second, optimizing the model for deployment on edge and mobile devices using frameworks such as TensorFlow Lite or ONNX will allow offline inference in low-connectivity regions. Third, integrating Internet-of-Things (IoT) sensor inputs—such as humidity, soil moisture, and temperature—could enable predictive analytics for disease outbreak prevention. Fourth, embedding explainable-AI modules to visualize affected leaf regions can increase user trust and interpretability. Finally, implementing multilingual interfaces and crop-specific advisory modules would broaden accessibility for farmers across different regions. In conclusion, the combination of CNN-based disease detection and Flask-driven deployment presents a scalable and adaptable solution for modern agriculture. With continued refinement through IoT integration, model optimization, and user-centric enhancements, this system can evolve into a comprehensive decision-support platform that promotes sustainable crop management, improves yield quality, and empowers farming communities worldwide. Funding Statement: This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors. Conflict of Interest: The authors declare that there are no conflicts of interest regarding the publication of this paper.

References

[1] Ahmad, S. Ali, and R. Khan, “A survey on using deep learning techniques for plant disease diagnosis,” Computers and Electronics in Agriculture, vol. 210, p. 108090, 2023. Available: https://www.sciencedirect.com/science/article/pii/S277237552200048X [2] A. Upadhyay et al., “Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture,” Artificial Intelligence Review, vol. 58, 2025. doi:10.1007/s10462-024-11100-x. [3] D. C. Rodríguez-Lira and J. M. Gómez, “Trends in machine and deep learning techniques for agriculture: A review,” Agriculture, vol. 14, no. 12, p. 2188, 2024. Available: https://www.mdpi.com/2077-0472/14/12/2188 [4] M. K. Elfouly, A. M. AbdelAziz, W. H. Gomaa, and M. Abdalla, “A deep learning-based framework for large-scale plant disease detection using big data analytics in precision agriculture,” Journal of Big Data, vol. 12, Art. no. 205, 2025. Available: https://journalofbigdata.springeropen.com/articles/10.1186/s40537-025-01265-9 [5] M. El Sakka, M. Ivanovici, L. Chaari, and J. Mothe, “A review of CNN applications in smart agriculture using multimodal data,” Sensors, vol. 25, no. 2, Art. no. 472, 2025. Available: https://www.mdpi.com/1424-8220/25/2/472 [6] M. I. Hossen, M. Awrangjeb, and S. Pan, “Transfer learning in agriculture: A review,” Artificial Intelligence Review, vol. 58, Art. no. 97, 2025. Available: https://link.springer.com/article/10.1007/s10462-024-11081-x [7] K. Mani and S. Gupta, “Deploying machine learning models via Flask web services: a review,” Journal of Web Engineering for Data Science, vol. 3, no. 1, pp. 45–59, 2024. Available: https://www.jweds.org/articles/view/2024-01-005 [8] M. Majdalawieh, “Precision agriculture in the age of AI: A systematic review,” Computers and Electronics in Agriculture, vol. 227, Art. no. 109557, 2024. Available: https://www.sciencedirect.com/science/article/pii/S0168169924005575 [9] M. M. Islam, M. M. Hasan, and S. R. Islam, “Deep learning-based crop disease prediction with web application,” Computers and Electronics in Agriculture, vol. 205, p. 107624, 2023. Available: https://www.sciencedirect.com/science/article/pii/S0168169923001456 [10] Z. Chen, X. Li, and Y. Zhou, “Plant disease recognition model based on improved YOLOv5,” Agronomy, vol. 12, no. 2, Art. no. 365, 2022. Available: https://www.mdpi.com/2073-4395/12/2/365 [11] Z. Liu, H. Li, and Q. Wang, “An improved YOLOv5-based apple leaf disease detection method,” Scientific Reports, vol. 14, Art. no. 1753, 2024. Available: https://www.nature.com/articles/s41598-024-1753-X [12] Y. Zhao, X. Xu, and C. Sun, “Precision detection of crop diseases based on improved YOLOv5 model,” Frontiers in Plant Science, vol. 13, Art. no. 946321, 2022. Available: https://www.frontiersin.org/articles/10.3389/fpls.2022.946321/full [13] A. H. Ali, H. R. Khan, and S. Shah, “An ensemble of deep-learning architectures for accurate plant disease classification,” IEEE Access, vol. 12, pp. 45021–45033, 2024. Available: https://ieeexplore.ieee.org/document/10453214 [14] H. N. Ngugi, F. K. Wakhungu, and P. O. Otieno, “Revolutionizing crop disease detection with computational deep learning: a comprehensive review,” Environmental Monitoring and Assessment, vol. 196, no. 3, Art. no. 325, 2024. Available: https://link.springer.com/article/10.1007/s10661-024-12454-z

Copyright

Copyright © 2025 Dr. Trupti Meshram, Pritam Waghmare, Sujal Gour, Yash Wadukale, Vishal Swain, Chirag Fulbandhe, Yash Tagde. This 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.