An Integrated Deep Learning Framework for Plant Disease Detection, Severity Analysis, and AI-Based Cure Recommendation

DOI

10.2991/978-94-6239-697-5_12How to use a DOI?

Keywords

Generative AI; CNN; Deep Learning

Abstract

Agriculture forms the foundation of human civilization and plays a critical role in ensuring global security of food. However, diseases in crops are caused by pathogens, fungi, and bacteria significantly reduce yield and quality [1], [6], [11]. Traditional visual inspection–based diagnosis is subjective, error-prone, and not scalable [3], [6]. To address these challenges, this paper presents PlantSarthi, an intelligent deep learning system for automated detection of disease in leaves of plant, severity estimation, and AI-assisted advisory generation. A Convolutional Neural Network (CNN) based on the VGG-19 architecture is employed to classify plant diseases from leaf images. Disease severity is estimated using Grad-CAM–based activation heatmap analysis [7], [10], where the spatial extent of disease-relevant regions is numerically quantified and categorized into mild, moderate, and severe levels. Additionally, a Generative AI module provides disease-specific precautionary and treatment suggestions to support farmer decision-making. Experimental evaluation on a publicly available plant disease dataset achieves a 85% classification accuracy, demonstrating the effectiveness and practical applicability of the proposed system for agricultural decision support.

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  - Akansha Agrawal
AU  - Ajay Suri
AU  - Kimmi Verma
PY  - 2026
DA  - 2026/06/04
TI  - An Integrated Deep Learning Framework for Plant Disease Detection, Severity Analysis, and AI-Based Cure Recommendation
BT  - Proceedings of the Conference on Bridging Engineering Disciplines with AI and Machine Learning (BEDAIML 2026)
PB  - Atlantis Press
SP  - 125
EP  - 136
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-697-5_12
DO  - 10.2991/978-94-6239-697-5_12
ID  - Agrawal2026
ER  -