AN ENSEMBLE-BASED CLUSTERING AND CLASSIFICATION FRAMEWORK FOR PREDICTING AGRICULTURAL CROP YIELD
DOI: https://doi.org/10.65725/JCISE/1/2/013
JOURNAL OF COMPUTATIONAL INTELLIGENCE SCIENCE AND ENGINEERING (JCISE)
ISSN: 3107-8168
Volume 1 Issue 2, October 2025
Abstract:
Accurate prediction of agricultural crop yield is essential for effective farm management, resource allocation, food security, and sustainable agricultural planning. However, crop yield is influenced by several interrelated factors, including soil characteristics, climatic conditions, rainfall, temperature, irrigation, fertilizer usage, and crop-specific attributes, making accurate prediction a challenging task.
This study proposes an ensemble-based clustering and classification framework for predicting agricultural crop yield using data mining techniques. The proposed framework initially applies clustering techniques to group agricultural data into homogeneous patterns based on environmental, soil, and crop-related characteristics. These clusters are subsequently used to improve the classification process by identifying yield categories such as low, medium, and high yield. Multiple machine learning classifiers are integrated through an ensemble learning approach to improve prediction stability and accuracy compared with individual models. The framework includes data preprocessing, feature selection, clustering, classification, ensemble model development, and performance evaluation. The study demonstrates the potential of data mining and ensemble learning techniques as an intelligent approach for improving agricultural yield prediction and supporting sustainable agriculture..
Authors: Udhaya priya J, Dr K Nirmala
Keywords: Agricultural Crop Yield Prediction, Data Mining, Clustering Techniques, Ensemble Learning, Machine Learning, Classification, Feature Selection, Sustainable Agriculture, Yield Prediction, Precision Agriculture.
