AI-Driven Solutions for Early Detection of Plant Diseases

Plant diseases have a major negative impact on crop yield and quality, making the agricultural sector concerned. Traditionally, plant disease detection is quite laborious and time consuming. The first introduced system is a deep learning-based plant disease identification system using Convolutional...

Full description

Saved in:
Bibliographic Details
Main Authors: Saha Laboni, Lalmawipuii R.
Format: Article
Language:English
Published: EDP Sciences 2025-01-01
Series:SHS Web of Conferences
Online Access:https://www.shs-conferences.org/articles/shsconf/pdf/2025/07/shsconf_iciaites2025_01076.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850119891288326144
author Saha Laboni
Lalmawipuii R.
author_facet Saha Laboni
Lalmawipuii R.
author_sort Saha Laboni
collection DOAJ
description Plant diseases have a major negative impact on crop yield and quality, making the agricultural sector concerned. Traditionally, plant disease detection is quite laborious and time consuming. The first introduced system is a deep learning-based plant disease identification system using Convolutional Neural Networks (CNNs). While the idea of artificial intelligence is catching up, a subfield of it known as deep learning is highly effective on tasks such as image recognition and classification. A CNN model is developed and trained in this research on a large annotated dataset of high-resolution plant images from different agricultural environments of healthy and diseased plants. Model architecture selection, data collection, preprocessing, training validation design are some key processes. Plant diseases were accurately detected and classified through fine tuning of the CNN model architecture. The performance was evaluated on standard metrics and good accuracy, sensitivity, specificity, precision, recall and Fl score were achieved. This approach shows the effectiveness in early and precise plant disease detection by results. Using AI driven tool for scalability and robustness, sustainable agricultural practices are supported and crop and food security is increased. The proposed system can help the widespread use of AI technologies in agriculture.
format Article
id doaj-art-cc5880f5693e487eabadb6f3d22fecc7
institution OA Journals
issn 2261-2424
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series SHS Web of Conferences
spelling doaj-art-cc5880f5693e487eabadb6f3d22fecc72025-08-20T02:35:32ZengEDP SciencesSHS Web of Conferences2261-24242025-01-012160107610.1051/shsconf/202521601076shsconf_iciaites2025_01076AI-Driven Solutions for Early Detection of Plant DiseasesSaha Laboni0Lalmawipuii R.1Department of CS & IT, Kalinga UniversityResearch Scholar, Department of CS & IT, Kalinga UniversityPlant diseases have a major negative impact on crop yield and quality, making the agricultural sector concerned. Traditionally, plant disease detection is quite laborious and time consuming. The first introduced system is a deep learning-based plant disease identification system using Convolutional Neural Networks (CNNs). While the idea of artificial intelligence is catching up, a subfield of it known as deep learning is highly effective on tasks such as image recognition and classification. A CNN model is developed and trained in this research on a large annotated dataset of high-resolution plant images from different agricultural environments of healthy and diseased plants. Model architecture selection, data collection, preprocessing, training validation design are some key processes. Plant diseases were accurately detected and classified through fine tuning of the CNN model architecture. The performance was evaluated on standard metrics and good accuracy, sensitivity, specificity, precision, recall and Fl score were achieved. This approach shows the effectiveness in early and precise plant disease detection by results. Using AI driven tool for scalability and robustness, sustainable agricultural practices are supported and crop and food security is increased. The proposed system can help the widespread use of AI technologies in agriculture.https://www.shs-conferences.org/articles/shsconf/pdf/2025/07/shsconf_iciaites2025_01076.pdf
spellingShingle Saha Laboni
Lalmawipuii R.
AI-Driven Solutions for Early Detection of Plant Diseases
SHS Web of Conferences
title AI-Driven Solutions for Early Detection of Plant Diseases
title_full AI-Driven Solutions for Early Detection of Plant Diseases
title_fullStr AI-Driven Solutions for Early Detection of Plant Diseases
title_full_unstemmed AI-Driven Solutions for Early Detection of Plant Diseases
title_short AI-Driven Solutions for Early Detection of Plant Diseases
title_sort ai driven solutions for early detection of plant diseases
url https://www.shs-conferences.org/articles/shsconf/pdf/2025/07/shsconf_iciaites2025_01076.pdf
work_keys_str_mv AT sahalaboni aidrivensolutionsforearlydetectionofplantdiseases
AT lalmawipuiir aidrivensolutionsforearlydetectionofplantdiseases