ADeepWeeD: An adaptive deep learning framework for weed species classification

Efficient weed management in agricultural fields is essential for attaining optimal crop yields and safeguarding global food security. Every year, farmers worldwide invest significant time, capital, and resources to combat yield losses, approximately USD 75.6 billion, due to weed infestations. Deep...

Full description

Saved in:
Bibliographic Details
Main Authors: Md Geaur Rahman, Md Anisur Rahman, Mohammad Zavid Parvez, Md Anwarul Kaium Patwary, Tofael Ahamed, David A. Fleming-Muñoz, Saad Aloteibi, Mohammad Ali Moni, PhD
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-12-01
Series:Artificial Intelligence in Agriculture
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589721725000492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387081100427264
author Md Geaur Rahman
Md Anisur Rahman
Mohammad Zavid Parvez
Md Anwarul Kaium Patwary
Tofael Ahamed
David A. Fleming-Muñoz
Saad Aloteibi
Mohammad Ali Moni, PhD
author_facet Md Geaur Rahman
Md Anisur Rahman
Mohammad Zavid Parvez
Md Anwarul Kaium Patwary
Tofael Ahamed
David A. Fleming-Muñoz
Saad Aloteibi
Mohammad Ali Moni, PhD
author_sort Md Geaur Rahman
collection DOAJ
description Efficient weed management in agricultural fields is essential for attaining optimal crop yields and safeguarding global food security. Every year, farmers worldwide invest significant time, capital, and resources to combat yield losses, approximately USD 75.6 billion, due to weed infestations. Deep Learning (DL) methodologies have been recently implemented to revolutionise agricultural practices, particularly in weed detection and classification. Existing DL-based weed classification techniques, including VGG16 and ResNet50, initially construct a model by implementing the algorithm on a training dataset comprising weed species, subsequently employing the model to identify weed species acquired during training. Given the dynamic nature of crop fields, we argue that existing methods may exhibit suboptimal performance due to two key issues: (i) the unavailability of all training weed species initially, as these species emerge over time, resulting in a progressively expanding training dataset, and (ii) the constrained memory and computational capacity of the system utilised for model development, which hinders the retention of all weed species that manifest over an extended duration. To address the issues, this paper introduces a novel DL-based framework called ADeepWeeD for weed classification that facilitates adaptive (i.e. incremental) learning so that it can handle new weed species by keeping track of historical information. ADeepWeeD is evaluated using two criteria, namely F1-Score and classification accuracy, by comparing its performances against four non-incremental and two incremental state-of-the-art methods on three publicly available large datasets. Our experimental results demonstrate that ADeepWeeD outperforms existing techniques used in this study. We believe that our developed model could be used to develop an automation system for weed identification. The code of the proposed method is available on GitHub: https://github.com/grahman20/ADeepWeed.
format Article
id doaj-art-5a7e96f1ad36443fbbd07f93ff9715a9
institution Kabale University
issn 2589-7217
language English
publishDate 2025-12-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Artificial Intelligence in Agriculture
spelling doaj-art-5a7e96f1ad36443fbbd07f93ff9715a92025-08-20T03:55:22ZengKeAi Communications Co., Ltd.Artificial Intelligence in Agriculture2589-72172025-12-0115459060910.1016/j.aiia.2025.04.009ADeepWeeD: An adaptive deep learning framework for weed species classificationMd Geaur Rahman0Md Anisur Rahman1Mohammad Zavid Parvez2Md Anwarul Kaium Patwary3Tofael Ahamed4David A. Fleming-Muñoz5Saad Aloteibi6Mohammad Ali Moni, PhD7School of Computing, Mathematics and Engineering, Charles Sturt University, Port Macquarie, NSW 2444, Australia; Corresponding author.La Trobe Business School, La Trobe University, Melbourne, VIC 3086, AustraliaSchool of Computing, Mathematics and Engineering, Charles Sturt University, Port Macquarie, NSW 2444, AustraliaSchool of Physics, Maths and Computing, The University of Western Australia, Perth, WA 6009, AustraliaFaculty of Life and Environmental Sciences, University of Tsukuba, Tsukuba Science City, 305-8572 Ibaraki, JapanLa Trobe Business School, La Trobe University, Melbourne, VIC 3086, AustraliaComputer Science Department, Community College, King Saud University, Riyadh, 11437, Saudi ArabiaAI & Digital Health Technology, Artificial Intelligence and Cyber Futures Institute, Charles Sturt University, Bathurst, NSW 2795, Australia; AI & Digital Health Technology, Rural Health Research Institute, Charles Sturt University, Orange, NSW 2800, Australia; School of IT, Washington University of Science and Technology, VA, USAEfficient weed management in agricultural fields is essential for attaining optimal crop yields and safeguarding global food security. Every year, farmers worldwide invest significant time, capital, and resources to combat yield losses, approximately USD 75.6 billion, due to weed infestations. Deep Learning (DL) methodologies have been recently implemented to revolutionise agricultural practices, particularly in weed detection and classification. Existing DL-based weed classification techniques, including VGG16 and ResNet50, initially construct a model by implementing the algorithm on a training dataset comprising weed species, subsequently employing the model to identify weed species acquired during training. Given the dynamic nature of crop fields, we argue that existing methods may exhibit suboptimal performance due to two key issues: (i) the unavailability of all training weed species initially, as these species emerge over time, resulting in a progressively expanding training dataset, and (ii) the constrained memory and computational capacity of the system utilised for model development, which hinders the retention of all weed species that manifest over an extended duration. To address the issues, this paper introduces a novel DL-based framework called ADeepWeeD for weed classification that facilitates adaptive (i.e. incremental) learning so that it can handle new weed species by keeping track of historical information. ADeepWeeD is evaluated using two criteria, namely F1-Score and classification accuracy, by comparing its performances against four non-incremental and two incremental state-of-the-art methods on three publicly available large datasets. Our experimental results demonstrate that ADeepWeeD outperforms existing techniques used in this study. We believe that our developed model could be used to develop an automation system for weed identification. The code of the proposed method is available on GitHub: https://github.com/grahman20/ADeepWeed.http://www.sciencedirect.com/science/article/pii/S2589721725000492Weed classificationAdaptive learningDeep learningArtificial intelligenceAgricultural automationPrecision agriculture
spellingShingle Md Geaur Rahman
Md Anisur Rahman
Mohammad Zavid Parvez
Md Anwarul Kaium Patwary
Tofael Ahamed
David A. Fleming-Muñoz
Saad Aloteibi
Mohammad Ali Moni, PhD
ADeepWeeD: An adaptive deep learning framework for weed species classification
Artificial Intelligence in Agriculture
Weed classification
Adaptive learning
Deep learning
Artificial intelligence
Agricultural automation
Precision agriculture
title ADeepWeeD: An adaptive deep learning framework for weed species classification
title_full ADeepWeeD: An adaptive deep learning framework for weed species classification
title_fullStr ADeepWeeD: An adaptive deep learning framework for weed species classification
title_full_unstemmed ADeepWeeD: An adaptive deep learning framework for weed species classification
title_short ADeepWeeD: An adaptive deep learning framework for weed species classification
title_sort adeepweed an adaptive deep learning framework for weed species classification
topic Weed classification
Adaptive learning
Deep learning
Artificial intelligence
Agricultural automation
Precision agriculture
url http://www.sciencedirect.com/science/article/pii/S2589721725000492
work_keys_str_mv AT mdgeaurrahman adeepweedanadaptivedeeplearningframeworkforweedspeciesclassification
AT mdanisurrahman adeepweedanadaptivedeeplearningframeworkforweedspeciesclassification
AT mohammadzavidparvez adeepweedanadaptivedeeplearningframeworkforweedspeciesclassification
AT mdanwarulkaiumpatwary adeepweedanadaptivedeeplearningframeworkforweedspeciesclassification
AT tofaelahamed adeepweedanadaptivedeeplearningframeworkforweedspeciesclassification
AT davidaflemingmunoz adeepweedanadaptivedeeplearningframeworkforweedspeciesclassification
AT saadaloteibi adeepweedanadaptivedeeplearningframeworkforweedspeciesclassification
AT mohammadalimoniphd adeepweedanadaptivedeeplearningframeworkforweedspeciesclassification