Advanced neural network architectures for tomato leaf disease diagnosis in precision agriculture

Abstract This study addresses the critical challenge of detecting and classifying tomato leaf diseases using advanced deep learning technologies, a pivotal step in enhancing productivity within precision agriculture. We developed a novel diagnostic system capable of categorizing tomato leaves into t...

Full description

Saved in:
Bibliographic Details
Main Authors: Hritwik Ghosh, Irfan Sadiq Rahat, Md. Mintajur Rahman Emon, Md. Jisan Mashrafi, Mohammed Abdul Al Arafat Tanzin, Sachi Nandan Mohanty, Shashi Kant
Format: Article
Language:English
Published: Springer 2025-04-01
Series:Discover Sustainability
Subjects:
Online Access:https://doi.org/10.1007/s43621-025-01149-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850172892272132096
author Hritwik Ghosh
Irfan Sadiq Rahat
Md. Mintajur Rahman Emon
Md. Jisan Mashrafi
Mohammed Abdul Al Arafat Tanzin
Sachi Nandan Mohanty
Shashi Kant
author_facet Hritwik Ghosh
Irfan Sadiq Rahat
Md. Mintajur Rahman Emon
Md. Jisan Mashrafi
Mohammed Abdul Al Arafat Tanzin
Sachi Nandan Mohanty
Shashi Kant
author_sort Hritwik Ghosh
collection DOAJ
description Abstract This study addresses the critical challenge of detecting and classifying tomato leaf diseases using advanced deep learning technologies, a pivotal step in enhancing productivity within precision agriculture. We developed a novel diagnostic system capable of categorizing tomato leaves into ten distinct classes—nine corresponding to specific diseases and one for healthy leaves. The system incorporates a dataset of 6,000 images, which underwent extensive preprocessing, including resizing to 256 × 256 pixels, grayscale conversion, normalization, masking, and augmentation, to optimize input quality for the model. Our approach stands out through the integration of state-of-the-art neural network architectures—VGG19, Vision Transformer (ViT), EfficientNetV2, ConvNeXt—and a novel hybrid model specifically designed to leverage the strengths of diverse architectures. Performance evaluation demonstrated that the hybrid model outperformed all individual architectures, achieving an exceptional classification accuracy of 98%, ensuring robust disease detection under varying conditions. To enhance interpretability, Grad-CAM and LIME techniques were employed, highlighting critical image regions and influential features for classification. This comprehensive and innovative approach not only deepens understanding in plant pathology through automated systems but also sets a new benchmark for future advancements in plant disease detection leveraging machine learning.
format Article
id doaj-art-02dbdc19eece40958fcf35b249d34fe6
institution OA Journals
issn 2662-9984
language English
publishDate 2025-04-01
publisher Springer
record_format Article
series Discover Sustainability
spelling doaj-art-02dbdc19eece40958fcf35b249d34fe62025-08-20T02:19:58ZengSpringerDiscover Sustainability2662-99842025-04-016113010.1007/s43621-025-01149-1Advanced neural network architectures for tomato leaf disease diagnosis in precision agricultureHritwik Ghosh0Irfan Sadiq Rahat1Md. Mintajur Rahman Emon2Md. Jisan Mashrafi3Mohammed Abdul Al Arafat Tanzin4Sachi Nandan Mohanty5Shashi Kant6School of Computer Science and Engineering (SCOPE), VIT-AP UniversitySchool of Computer Science and Engineering (SCOPE), VIT-AP UniversityDepartment of Computer Science and Engineering, American International University-BangladeshDepartment of Computer Science and Engineering, Brac UniversityDepartment of Computer Science and Engineering, Brac UniversitySchool of Computer Science and Engineering (SCOPE), VIT-AP UniversityDepartment of Management, College of Business and Economics, Bule Hora UniversityAbstract This study addresses the critical challenge of detecting and classifying tomato leaf diseases using advanced deep learning technologies, a pivotal step in enhancing productivity within precision agriculture. We developed a novel diagnostic system capable of categorizing tomato leaves into ten distinct classes—nine corresponding to specific diseases and one for healthy leaves. The system incorporates a dataset of 6,000 images, which underwent extensive preprocessing, including resizing to 256 × 256 pixels, grayscale conversion, normalization, masking, and augmentation, to optimize input quality for the model. Our approach stands out through the integration of state-of-the-art neural network architectures—VGG19, Vision Transformer (ViT), EfficientNetV2, ConvNeXt—and a novel hybrid model specifically designed to leverage the strengths of diverse architectures. Performance evaluation demonstrated that the hybrid model outperformed all individual architectures, achieving an exceptional classification accuracy of 98%, ensuring robust disease detection under varying conditions. To enhance interpretability, Grad-CAM and LIME techniques were employed, highlighting critical image regions and influential features for classification. This comprehensive and innovative approach not only deepens understanding in plant pathology through automated systems but also sets a new benchmark for future advancements in plant disease detection leveraging machine learning.https://doi.org/10.1007/s43621-025-01149-1Hybrid modelGrad-CAMLIME techniquesArchitecturesVision Transformer
spellingShingle Hritwik Ghosh
Irfan Sadiq Rahat
Md. Mintajur Rahman Emon
Md. Jisan Mashrafi
Mohammed Abdul Al Arafat Tanzin
Sachi Nandan Mohanty
Shashi Kant
Advanced neural network architectures for tomato leaf disease diagnosis in precision agriculture
Discover Sustainability
Hybrid model
Grad-CAM
LIME techniques
Architectures
Vision Transformer
title Advanced neural network architectures for tomato leaf disease diagnosis in precision agriculture
title_full Advanced neural network architectures for tomato leaf disease diagnosis in precision agriculture
title_fullStr Advanced neural network architectures for tomato leaf disease diagnosis in precision agriculture
title_full_unstemmed Advanced neural network architectures for tomato leaf disease diagnosis in precision agriculture
title_short Advanced neural network architectures for tomato leaf disease diagnosis in precision agriculture
title_sort advanced neural network architectures for tomato leaf disease diagnosis in precision agriculture
topic Hybrid model
Grad-CAM
LIME techniques
Architectures
Vision Transformer
url https://doi.org/10.1007/s43621-025-01149-1
work_keys_str_mv AT hritwikghosh advancedneuralnetworkarchitecturesfortomatoleafdiseasediagnosisinprecisionagriculture
AT irfansadiqrahat advancedneuralnetworkarchitecturesfortomatoleafdiseasediagnosisinprecisionagriculture
AT mdmintajurrahmanemon advancedneuralnetworkarchitecturesfortomatoleafdiseasediagnosisinprecisionagriculture
AT mdjisanmashrafi advancedneuralnetworkarchitecturesfortomatoleafdiseasediagnosisinprecisionagriculture
AT mohammedabdulalarafattanzin advancedneuralnetworkarchitecturesfortomatoleafdiseasediagnosisinprecisionagriculture
AT sachinandanmohanty advancedneuralnetworkarchitecturesfortomatoleafdiseasediagnosisinprecisionagriculture
AT shashikant advancedneuralnetworkarchitecturesfortomatoleafdiseasediagnosisinprecisionagriculture