Deep learning-based crop health enhancement through early disease prediction

Manual disease detection methods currently in use are laborious, time-intensive, and heavily reliant on specialized knowledge. The urgent need to address these challenges motivates this study. The primary goal of this research is to develop a model capable of accurately distinguishing between health...

Full description

Saved in:
Bibliographic Details
Main Authors: Venkata Santhosh Yakkala, Krishna Vamsi Nusimala, Badisa Gayathri, Sriya Kanamarlapudi, S. S. Aravinth, Ayodeji Olalekan Salau, S. Srithar
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Cogent Food & Agriculture
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/23311932.2024.2423244
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850098981440323584
author Venkata Santhosh Yakkala
Krishna Vamsi Nusimala
Badisa Gayathri
Sriya Kanamarlapudi
S. S. Aravinth
Ayodeji Olalekan Salau
S. Srithar
author_facet Venkata Santhosh Yakkala
Krishna Vamsi Nusimala
Badisa Gayathri
Sriya Kanamarlapudi
S. S. Aravinth
Ayodeji Olalekan Salau
S. Srithar
author_sort Venkata Santhosh Yakkala
collection DOAJ
description Manual disease detection methods currently in use are laborious, time-intensive, and heavily reliant on specialized knowledge. The urgent need to address these challenges motivates this study. The primary goal of this research is to develop a model capable of accurately distinguishing between healthy and diseased crop leaves. Additionally, the model aims to identify specific diseases affecting the crops if they are found to be diseased. Leveraging the power of machine learning algorithms, particularly Convolutional Neural Networks (CNNs) and ResNet-9 architecture, this research seeks to transform the process of detecting plant diseases. It focuses on analyzing diverse morphological features such as color, intensity, and dimensions in plant leaves to enable quick and accurate classification. By introducing AI-driven systems into agricultural practices, this study aims to revolutionize disease identification, prediction, and management. The overarching objective is to minimize crop losses and enhance agricultural productivity. In addition to highlighting the significance of machine learning techniques such as ResNet-9, this study emphasizes the importance of environmentally friendly biological control methods for regulating pests and diseases in agricultural settings. The adoption of Convolutional Neural Networks, specifically the ResNet-9 architecture, signifies a significant advancement in predicting plant diseases. This approach holds the promise of vastly improving the accuracy and efficiency of disease forecasting within the agricultural domain.
format Article
id doaj-art-8f922f2b16d34852b29fa1a0a271a6e4
institution DOAJ
issn 2331-1932
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Cogent Food & Agriculture
spelling doaj-art-8f922f2b16d34852b29fa1a0a271a6e42025-08-20T02:40:35ZengTaylor & Francis GroupCogent Food & Agriculture2331-19322025-12-0111110.1080/23311932.2024.2423244Deep learning-based crop health enhancement through early disease predictionVenkata Santhosh Yakkala0Krishna Vamsi Nusimala1Badisa Gayathri2Sriya Kanamarlapudi3S. S. Aravinth4Ayodeji Olalekan Salau5S. Srithar6Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Andhra Pradesh, IndiaDepartment of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Andhra Pradesh, IndiaDepartment of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Andhra Pradesh, IndiaDepartment of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Andhra Pradesh, IndiaDepartment of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Andhra Pradesh, IndiaDepartment of Electrical/Electronics and Computer Engineering, Afe Babalola University, Ado-Ekiti, NigeriaDepartment of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Andhra Pradesh, IndiaManual disease detection methods currently in use are laborious, time-intensive, and heavily reliant on specialized knowledge. The urgent need to address these challenges motivates this study. The primary goal of this research is to develop a model capable of accurately distinguishing between healthy and diseased crop leaves. Additionally, the model aims to identify specific diseases affecting the crops if they are found to be diseased. Leveraging the power of machine learning algorithms, particularly Convolutional Neural Networks (CNNs) and ResNet-9 architecture, this research seeks to transform the process of detecting plant diseases. It focuses on analyzing diverse morphological features such as color, intensity, and dimensions in plant leaves to enable quick and accurate classification. By introducing AI-driven systems into agricultural practices, this study aims to revolutionize disease identification, prediction, and management. The overarching objective is to minimize crop losses and enhance agricultural productivity. In addition to highlighting the significance of machine learning techniques such as ResNet-9, this study emphasizes the importance of environmentally friendly biological control methods for regulating pests and diseases in agricultural settings. The adoption of Convolutional Neural Networks, specifically the ResNet-9 architecture, signifies a significant advancement in predicting plant diseases. This approach holds the promise of vastly improving the accuracy and efficiency of disease forecasting within the agricultural domain.https://www.tandfonline.com/doi/10.1080/23311932.2024.2423244Agroecosystem resiliencephyto pathological analysismultispectral imagingprecision agriculturefeature engineeringanomaly detection
spellingShingle Venkata Santhosh Yakkala
Krishna Vamsi Nusimala
Badisa Gayathri
Sriya Kanamarlapudi
S. S. Aravinth
Ayodeji Olalekan Salau
S. Srithar
Deep learning-based crop health enhancement through early disease prediction
Cogent Food & Agriculture
Agroecosystem resilience
phyto pathological analysis
multispectral imaging
precision agriculture
feature engineering
anomaly detection
title Deep learning-based crop health enhancement through early disease prediction
title_full Deep learning-based crop health enhancement through early disease prediction
title_fullStr Deep learning-based crop health enhancement through early disease prediction
title_full_unstemmed Deep learning-based crop health enhancement through early disease prediction
title_short Deep learning-based crop health enhancement through early disease prediction
title_sort deep learning based crop health enhancement through early disease prediction
topic Agroecosystem resilience
phyto pathological analysis
multispectral imaging
precision agriculture
feature engineering
anomaly detection
url https://www.tandfonline.com/doi/10.1080/23311932.2024.2423244
work_keys_str_mv AT venkatasanthoshyakkala deeplearningbasedcrophealthenhancementthroughearlydiseaseprediction
AT krishnavamsinusimala deeplearningbasedcrophealthenhancementthroughearlydiseaseprediction
AT badisagayathri deeplearningbasedcrophealthenhancementthroughearlydiseaseprediction
AT sriyakanamarlapudi deeplearningbasedcrophealthenhancementthroughearlydiseaseprediction
AT ssaravinth deeplearningbasedcrophealthenhancementthroughearlydiseaseprediction
AT ayodejiolalekansalau deeplearningbasedcrophealthenhancementthroughearlydiseaseprediction
AT ssrithar deeplearningbasedcrophealthenhancementthroughearlydiseaseprediction