<![CDATA[This study aims to identify and cluster agricultural areas in Southeast Aceh Regency using the Gaussian Mixture Model (GMM) algorithm. The dataset consists of village-level agricultural data, including land area, production volume, productivity, and the number of farmers. To ensure comparability across variables, Z-Score normalization was applied. The optimal number of clusters was determined using the Bayesian Information Criterion (BIC), resulting in three distinct groups: high, medium, and low production areas. Clustering performance was evaluated using the Silhouette Score (0.3893) and the Davies-Bouldin Index (0.8548), indicating moderate clustering quality with reasonable separation between clusters. To improve accessibility and practical use, a web-based information system was developed to visualize agricultural data, clustering outcomes, and evaluation metrics interactively. These findings highlight the value of GMM-based machine learning in supporting data-driven decision-making and prioritizing agricultural development efforts by local governments.]]>
Copyrights © 2026
