Intelligent Multimodal Framework for Explainable Plant Disease Diagnosis and Treatment Recommendation

DOI

10.2991/978-94-6239-678-4_9How to use a DOI?

Keywords

Agentic AI; Multimodal Reasoning; Explainable Diagnosis; Precision Agriculture; Knowledge Retrieval

Abstract

Plant diseases continue to pose a significant challenge to food security in the world and this has resulted into extensive loss in crop yield and financial instability among agricultural communities. The conventional approaches to the disease diagnosis are based on manual examination by specialists and are thus time-consuming, subjective, and can never be done at large-scale levels. Most of the existing systems, even recent developments that have achieved significant progress in automated plant disease recognition using leaf image as the single-modality visual input, cannot operate with contextual reasoning, interpretability, and adaptable decision-making, although recent progress in deep learning, especially Convolutional Neural Networks (CNNs) and YOLO-based architectures, has substantially increased the accuracy and effectiveness of automated plant disease recognition. In order to overcome these drawbacks, this paper presents an Agentic AI Framework, which combines visual crop image analysis, natural language symptom description, and structured agricultural knowledge to provide explainable and reliable plant disease diagnosis. The model makes use of coordinated autonomous agents that perform the functions of vision perception, language understanding, multimodal fusion, retrieval-augmented reasoning, and treatment planning. The system is capable of predicting the diseases with accuracy and giving evidence-based and practical treatment recommendations by using the authoritative agronomic resources of ICAR and FAO. Evidence-based on experimental validation of the proposed framework on the basis of PlantVillage and PlantDoc databases proves a higher accuracy of the diagnostics, as well as greater trust, making the given framework a comprehensive decision-support system of sustainable and reasonable crop management.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ayesha Butalia
AU  - Yash Nimbalkar
AU  - Reena Gunjan
PY  - 2026
DA  - 2026/05/28
TI  - Intelligent Multimodal Framework for Explainable Plant Disease Diagnosis and Treatment Recommendation
BT  - Proceedings of the 2nd International Conference on Recent Advancement and Modernization in Sustainable Intelligent Technologies & Applications (RAMSITA-2026)
PB  - Atlantis Press
SP  - 103
EP  - 114
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-678-4_9
DO  - 10.2991/978-94-6239-678-4_9
ID  - Butalia2026
ER  -