Advancing site-specific disease and pest management in precision agriculture: From reasoning-driven foundation models to adaptive, feedback-based learning

TL;DR

This paper reviews recent advances in site-specific disease management in precision agriculture, emphasizing foundation models, multi-modal learning, and adaptive feedback systems to improve real-time crop health monitoring and targeted interventions.

Contribution

It provides a comprehensive overview of how foundation models and multi-modal AI are transforming SSDM, highlighting emerging trends, challenges, and future directions in adaptive, feedback-based learning.

Findings

FMs are increasingly adopted in SSDM with rapid growth in 2023-24.

Vision-language models outperform language-only models in disease detection.

Reinforcement learning and digital twins are emerging but still in early stages for targeted spraying.

Abstract

Site-specific disease management (SSDM) in crops has advanced rapidly through machine and deep learning (ML and DL) for real-time computer vision. Research evolved from handcrafted feature extraction to large-scale automated feature learning. With foundation models (FMs), crop disease datasets are now processed in fundamentally new ways. Unlike traditional neural networks, FMs integrate visual and textual data, interpret symptoms in text, reason about symptom-management relationships, and support interactive QA for growers and educators. Adaptive and imitation learning in robotics further enables field-based disease management. This review screened approx. 40 articles on FM applications for SSDM, focusing on large-language models (LLMs) and vision-language models (VLMs), and discussing their role in adaptive learning (AL), reinforcement learning (RL), and digital twin frameworks for targeted spraying. Key findings: (a) FMs are gaining traction with surging literature in 2023-24; (b) VLMs outpace LLMs, with a 5-10x increase in publications; (c) RL and AL are still nascent for smart spraying; (d) digital twins with RL can simulate targeted spraying virtually; (e) addressing the sim-to-real gap is critical for real-world deployment; (f) human-robot collaboration remains limited, especially in human-in-the-loop approaches where robots detect early symptoms and humans validate uncertain cases; (g) multi-modal FMs with real-time feedback will drive next-gen SSDM. For updates, resources, and contributions, visit, https://github.com/nitin-dominic/AgriPathogenDatabase, to submit papers, code, or datasets.