TY - JOUR
T1 - ADeepWeeD
T2 - An adaptive deep learning framework for weed species classification
AU - Rahman, Gea
AU - Rahman, Md Anisur
AU - Parvez, Mohammad Zavid
AU - Patwary, Md Anwarul Kaium
AU - Ahamed, Tofael
AU - Fleming-Muñoz, David A.
AU - Aloteibi, Saad
AU - Moni, Mohammad Ali
PY - 2025/5/22
Y1 - 2025/5/22
N2 - 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
AB - 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
KW - Weed classification
KW - Adaptive learning
KW - Deep learning
KW - Artificial intelligence
KW - gricultural automation
KW - Precision agriculture
UR - https://www.sciencedirect.com/science/article/pii/S2589721725000492
U2 - 10.1016/j.aiia.2025.04.009
DO - 10.1016/j.aiia.2025.04.009
M3 - Article
SN - 2589-7217
VL - 15
SP - 590
EP - 609
JO - Artificial Intelligence in Agriculture
JF - Artificial Intelligence in Agriculture
IS - 4
ER -
