Coconut Tree Disease Detection and Management Using Machine Learning
Shapurabegum Imamsab Shalavadi
, Ashwini Garaddi
Coconut Disease Detection
Abstract: Coconut cultivation plays an important role in agriculture and contributes significantly to food production and rural economies in many tropical countries. However, coconut plantations are highly vulnerable to various leaf diseases and pest infestations that negatively affect plant health, crop productivity, and economic yield. Traditional disease identification methods generally rely on manual inspection by agricultural experts, which can be time-consuming, labor-intensive, and prone to human error. Therefore, intelligent and automated disease detection systems have become increasingly important in modern precision agriculture.
This project presents a Coconut Leaf Disease Detection and Management System using Deep Learning and Stream lit Web Application. The system utilizes image-based disease diagnosis to classify coconut leaf conditions into five categories: CCI_Caterpillars,Healthy_Leaves,CLWD_ Drying of Leaflets_Flaccidity, and WCLWD_Yellowing. The project employs Transfer Learning using MobileNetV2, a pretrained deep learning architecture, to improve disease classification accuracy while reducing training complexity and computational requirements.
The dataset undergoes preprocessing and augmentation techniques including image rescaling, rotation, zooming, width shifting, height shifting, and horizontal piping. These preprocessing operations improve model generalization and increase robustness against image variations. Training and validation datasets are created using Image Data Generator to support systematic model learning and evaluation.
The pretrained MobileNetV2 model is used as the feature extraction backbone while additional fully connected layers are added for coconut disease classification. The model is trained using the Adam optimizer and categorical cross-entropy loss function. Early stopping is incorporated to prevent overfitting and improve model stability. Training performance is monitored using accuracy and loss graphs.
Index Terms— CLWD, WCLWD
"Coconut Tree Disease Detection and Management Using Machine Learning", JETNR - JOURNAL OF EMERGING TRENDS AND NOVEL RESEARCH (www.JETNR.org), ISSN:2984-9276, Vol.4, Issue 6, page no.a351-a359, June-2026, Available :https://rjpn.org/JETNR/papers/JETNR2606048.pdf
Volume 4
Issue 6,
June-2026
Pages : a351-a359
Paper Reg. ID: JETNR_235018
Published Paper Id: JETNR2606048
Downloads: 000107
Research Area: Science and Technology
Country: Nargund/Gadag, Karnataka, India
DOI: https://doi.org/10.56975/jetnr.v4i6.235018
ISSN: 2984-9276 | IMPACT FACTOR: 9.87 Calculated By Google Scholar | ESTD YEAR: 2023
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.87 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: RJPN (IJPublication) Janvi Wave
