Automated Plant Health Disease Management and Smart Monitoring Using Deep Learning Models

DOI

10.2991/978-94-6463-738-0_5How to use a DOI?

Keywords

Sprig Recognition; Deep Learning Models; Automated Agriculture; Image-Based Disease Diagnosis; Convolutional Neural Network

Abstract

This work investigates the usage of deep learning algorithms for automated identification and recognition for plant leaf diseases to improve plant sprig health management. Food security and global agriculture are under grave risk due to the spread of plant diseases. In order to create effective mitigation strategies, these illnesses must be appropriately and quickly diagnosed. Deep learning has showed promise in automating this critical procedure since it can uncover patterns from enormous datasets. Deep learning software that can reliably identify plant sprig concerns in pictures is being developed. To acquire a wide range of plant sprig photos, both healthy and sick. To assess the models’ F1-score, accuracy, recall, and precision. To investigate deep learning models’ capacity to recognize and diagnose certain diseases, as well as the severity of such ailments. A convolutional neural network (CNNs) was the principal deep learning architecture employed in the study. Images that have been pre-processed feature both healthy and damaged leaves from a range of plants. Transfer learning is used with pre-trained CNN models to quicken model convergence and increase performance. Several experiments are carried out in order to improve training methodologies, change hyperparameters, and assess how well the models classify and diagnose disorders. Disease-specific algorithms are being developed to better classify and measure the severity of disorders. The outcomes of our study show in what way deep learning influence to be used to automatically identify and categorize plant leaf diseases. The generated models are quite excellent at spotting illnesses and differentiating them from healthy leaves. Some diseases may be accurately classified and their se verity levels determined using sickness classification algorithms. By enhancing automated plant health monitoring, we provide a vital tool for premature disease detection and proactive agricultural managing. The discoveries are likely to support sustainable farming practices and increase global food security since they can dramatically decrease the possessions of plant diseases onto crop yields and food supplies.

Copyright

© 2025 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  - Pellakuri Vidyullatha
AU  - G. S. Pradeep Ghantasala
AU  - R. Rajesh Sharma
AU  - Gaganpreet Kaur
AU  - Akey Sungheetha
PY  - 2025
DA  - 2025/06/22
TI  - Automated Plant Health Disease Management and Smart Monitoring Using Deep Learning Models
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 44
EP  - 57
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_5
DO  - 10.2991/978-94-6463-738-0_5
ID  - Vidyullatha2025
ER  -