Use of Generative AI, Advanced Computer Vision, and Predictive Analytics in Agriculture: Applications, Evidence, and Open Challenges
Journal of Advanced Engineering Technology and Management
Volume: 2 Issue: 1 | Open Access | 20 Feb 2026
Use of Generative AI, Advanced Computer Vision, and Predictive Analytics in Agriculture: Applications, Evidence, and Open Challenges
Akhil Hasan, Software Engineer and Independent Researcher, Dell India
Abstract: This paper reviews how three converging AI capabilities — (1) generative AI (large language and multimodal models and synthetic-data generators), (2) advanced computer vision (CV) with UAV/satellite and multispectral sensing, and (3) predictive analytics for forecasting and decision support — are being applied in modern agriculture. We focus on representative applications (disease/pest detection, yield prediction, advisory chatbots, data augmentation, and decision-support pipelines), summarize the empirical evidence for benefits, and synthesize the main technical, ethical, and deployment challenges.
Keywords: generative AI, synthetic data, computer vision, UAV remote sensing, precision agriculture, predictive analytics, AgroLLM, data fusion
References
Akkem, Y., et al. (2024). A comprehensive review of synthetic data generation in agriculture. ScienceDirect.
Kouadio, L., et al. (2023). UAV-based applications for plant disease detection. Remote Sensing, MDPI.
Krupitzer, C., et al. (2024). Generative artificial intelligence in the agri-food value chain. Frontiers in Food Science & Technology.
Mano, S., et al. (2025). AgroLLM: Retrieval-augmented language models for agricultural advisory systems. arXiv.
Shahi, T. B., et al. (2023). Recent advances in crop disease detection using UAV remote sensing. Remote Sensing, MDPI.
Soussi, A., et al. (2024). Smart sensors and smart data for precision agriculture. Sensors, MDPI.
Springer. (2026). Synthetic Image Generation for Crop Disease Classification. Springer.