Integrating LightGBM and XGBoost for Robust Plant Disease Classification: A Homogenous Stacking Approach

Title

Integrating LightGBM and XGBoost for Robust Plant Disease Classification: A Homogenous Stacking Approach

Creator

George, Jossy; Yadav, Jai; Nair, Akhil M.

Description

In addressing the critical challenge of early and accurate plant disease diagnosis, this study explores the application of a novel homogeneous multi-layered stacking model utilising Light Gradient Boosting Model (LGBM) and Extreme Gradient Boost (XGB) for the detection of plant diseases. Traditional approaches often rely on basic stacking methods; however, this research seeks to explore the intricacies of altering model architecture, combining the strengths of LGBM and XGB classifiers to build a highly accurate and efficient disease detection system. Comprehensive evaluations were conducted using metrics such as AUCROC curves, Confusion matrix and F1 scores. The ROC curve for the stacked model demonstrated superior performance with a score of 85.12%, compared to 83.09% for the single LightGBM model used for comparative analysis. The future scope of ML in agriculture includes integrating such models with real-time monitoring systems and expanding its applications to diverse crops and environments. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

Source

Lecture Notes in Networks and Systems;Volume;1377 LNNS;pp.409-422

Date

01-01-2025

Publisher

Springer Science and Business Media Deutschland GmbH

Subject

AUCROC curve; Confusion matrix; F1 score; Homogenous stacking; Plant disease prediction

Coverage

George J., CHRIST (Deemed to Be University), Delhi NCR Campus, Ghaziabad, India; Yadav J., CHRIST (Deemed to Be University), Delhi NCR Campus, Ghaziabad, India; Nair A.M., CHRIST (Deemed to Be University), Delhi NCR Campus, Ghaziabad, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 23673370; ISBN: 978-981965369-0;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1007/978-981-96-5370-6_30

https://www.scopus.com/pages/publications/105018796519?origin=resultslist