A Survey on AI-Driven Crop Disease Prediction and Management for Sustainable Agriculture

Abstract

Agriculture is a vital sector that faces substantial challenges due to crop diseases, affecting both productivity and the livelihood of farmers. Traditional methods for identifying and managing crop diseases are often labor-intensive, time-consuming, and lack the precision required for effective mitigation. This survey paper presents an overview of recent advancements in AI-driven crop disease prediction and management systems, focusing on their transformative potential in modern agriculture. The study explores the integration of deep learning models, such as MobileNetV2, for image-based disease detection and highlights the role of environmental data—temperature, humidity, and weather conditions—in improving predictive accuracy. Key features such as real-time alerts, multilingual support, and treatment recommendations tailored for specific crops (e.g., cotton, sugarcane, soybean) are discussed, alongside potential deployment challenges and data requirements. Additionally, we review existing solutions, architectural frameworks, and methodologies to provide insights into the system\'s development and the scalability needed for diverse agricultural contexts. The paper concludes by addressing future directions, including the implementation of a subscription model for agronomist support, an integrated e-marketplace, and economic considerations for system sustainability. This survey underscores the importance of AI in enhancing crop resilience and supporting farmers with accurate, timely, and accessible disease management tools.

Introduction

The growing global population and climate change have increased challenges for farmers, especially in identifying and managing plant diseases that threaten crop yield, quality, and food security. Traditional manual diagnosis is slow and subjective, but advances in technology, particularly machine learning and image recognition (e.g., convolutional neural networks or CNNs), offer promising tools for early disease detection. Despite their effectiveness, these AI models face issues like data scarcity, limited interpretability, and challenges in accuracy across diverse crops and environments.

Smart agriculture, incorporating AI, IoT, sensors, and drones, represents a technological revolution aimed at improving crop monitoring, resource optimization, and sustainable farming. Various studies have shown high accuracy in disease detection using deep learning models trained on large image datasets.

Existing AI-powered systems like PlantVillage and PlantNet help farmers diagnose diseases by uploading crop images. However, challenges remain, including limited data accessibility, poor user experience for non-experts, model generalization, and sustainability concerns. The proposed system integrates multiple data sources—crop images, environmental factors, and expert insights—using deep learning to provide real-time disease diagnosis, treatment recommendations, and sustainable farming guidance through an easy-to-use mobile app.

The system aims to empower farmers, particularly in resource-limited settings, to reduce crop losses and promote long-term environmental health. Future developments may include expanded crop coverage, drone integration, blockchain for supply chain transparency, multi-language support, offline capabilities, and enhanced predictive analytics to support market planning and policy-making.

Conclusion

This survey emphasizes the transformative potential of AI-driven crop disease prediction and management systems in revolutionizing agricultural practices in India. By providing farmers with real-time, data-driven insights into crop health, weather conditions, and disease prevention, the system aims to enhance productivity, reduce crop losses, and promote sustainable farming practices. The integration of machine learning for early disease detection and future advancements, such as drone-based monitoring and blockchain for supply chain transparency, further strengthens the system’s impact. Ultimately, this approach not only supports farmers in making informed decisions but also contributes to the long-term sustainability of agriculture, food security, and rural economic growth

References

[1] N. Nigar, H. Muhammad Faisal, M. Umer, O. Oki and J. Manappattukunnel Lukose, \"Improving Plant Disease Classification With Deep-Learning-Based Prediction Model Using Explainable Artificial Intelligence,\" in IEEE Access, vol. 12, pp. 100005-100014, 2024, doi: 10.1109/ACCESS.2024.3428553. [2] M. Louta, K. Banti and I. Karampelia, \"Emerging Technologies for Sustainable Agriculture: The Power of Humans and the Way Ahead,\" in IEEE Access, vol. 12, pp. 98492-98529, 2024, doi: 10.1109/ACCESS.2024.3428401. [3] T. Mahmud et al., \"An Approach for Crop Prediction in Agriculture: Integrating Genetic Algorithms and Machine Learning,\" in IEEE Access, doi: 10.1109/ACCESS.2024.3478739. [4] A. A. AlZubi and K. Galyna, \"Artificial Intelligence and Internet of Things for Sustainable Farming and Smart Agriculture,\" in IEEE Access, vol. 11, pp. 78686-78692, 2023, doi: 10.1109/ACCESS.2023.3298215. [5] R. Rani, J. Sahoo, S. Bellamkonda, S. Kumar and S. K. Pippal, \"Role of Artificial Intelligence in Agriculture: An Analysis and Advancements With Focus on Plant Diseases,\" in IEEE Access, vol. 11, pp. 137999-138019, 2023, doi: 10.1109/ACCESS.2023.3339375. [6] E. Elbasi et al., \"Artificial Intelligence Technology in the Agricultural Sector: A Systematic Literature Review,\" in IEEE Access, vol. 11, pp. 171-202, 2023, doi: 10.1109/ACCESS.2022.3232485. [7] S. I. Hassan, M. M. Alam, U. Illahi, M. A. Al Ghamdi, S. H. Almotiri and M. M. Su’ud, \"A Systematic Review on Monitoring and Advanced Control Strategies in Smart Agriculture,\" in IEEE Access, vol. 9, pp. 32517-32548, 2021, doi: 10.1109/ACCESS.2021.3057865. [8] V. K. Vishnoi, K. Kumar, and B. Kumar, ‘‘Plant disease detection using computational intelligence and image processing,’’ J. Plant Diseases Protection, vol. 128, pp. 19–53, Aug. 2021. [9] S. Kinger and V. Kulkarni, ‘‘Explainable ai for deep learning based disease detection,’’ in Proc. 13th Int. Conf. Contemp. Comput. (IC), 2021, pp. 209–216. [10] K. P. Ferentinos, ‘‘Deep learning models for plant disease detection and diagnosis,’’ Comput. Electron. Agricult., vol. 145, pp. 311–318, Feb. 2018. [11] M. H. K. Mehedi, A. K. M. S. Hosain, S. Ahmed, S. T. Promita, R. K. Muna, M. Hasan, and M. T. Reza, ‘‘Plant leaf disease detection using transfer learning and explainable AI,’’ in Proc. IEEE 13th Annu. Inf. Technol., Electron. Mobile Commun. Conf. (IEMCON), Oct. 2022, pp. 0166–0170. [12] S. Bhattarai. New Plant Diseases Dataset. [Online]. Available: https://www.kaggle.com/datasets/vipoooool/new-plant-diseases-dataset [13] S. P. Mohanty, D. P. Hughes, and M. Salathé, ‘‘Using deep learning for image-based plant disease detection,’’ Frontiers Plant Sci., vol. 7, p. 1419, Sep. 2016. [14] S. Mohanty. PlantVillage Dataset. [Online]. Available: https://github.com/salathegroup/plantvillage_deeplearning_paper_dataset [15] S. Ramesh, R. Hebbar, M. Niveditha, R. Pooja, N. Shashank, and P. V. Vinod, ‘‘Plant disease detection using machine learning,’’ in Proc.Int. Conf. Design Innov. 3Cs Compute Communicate Control (ICDI3C), Apr. 2018, pp. 41–45.

Copyright

Copyright © 2025 Ganesh Kulkarni, Atul Patil, Sahil Gorade, Abhijeet Nirphal, Prof. Rekha Kotwal. 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.