V2I9P4

Survey and Comparative Analysis of Machine Learning Classifiers for Coconut Tree Disease Prediction with WEKA

S.T. Pavithra Devi^1*, Dr. V. Maniraj²

Abstract

Coconut trees are a vital source of livelihood, nutrition, and economic support for millions of farmers worldwide. However, their productivity is often threatened by diseases that are difficult to detect in the early stages through traditional methods. Machine learning (ML) offers a promising way to address this challenge by transforming agricultural data into accurate, timely predictions. This study explores the potential of WEKA, a widely used machine learning tool, to predict coconut tree diseases. A comparative analysis of classifiers such as Support Vector Machines (SVM), Random Forests (RF), J48 decision trees, and NaIve Bayes was conducted to evaluate their performance in disease classification. The models were assessed based on accuracy, precision, recall, and F1-score to identify the most effective approach for real-world application. Results highlight the strengths and limitations of each classifier, offering practical insights into how ML can support early detection and intervention. By bridging technology with agriculture, this study demonstrates how accessible ML tools like WEKA can help farmers adopt smarter, more sustainable practices in coconut plantation management.

Keywords:

Coconut tree disease prediction, Machine learning classifiers, WEKA, Comparative analysis