<![CDATA[Rainfall is an important weather parameter that affects various sectors, including agriculture, transportation, and disaster mitigation. As a tropical region, Palembang experiences varying rainfall patterns, making effective rainfall classification essential. However, previous studies have generally focused on specific machine learning methods, used a limited number of weather variables, or classified rainfall into only two categories. These differences make it difficult to understand how various machine learning methods perform when applied to multiclass rainfall classification using more complete meteorological data. Therefore, this study aims to classify rainfall in Palembang using machine learning methods, namely Random Forest, Decision Tree, Naïve Bayes, K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). The dataset used in this study consists of meteorological data obtained from the Sultan Mahmud Badaruddin II Meteorological Station, Palembang, with an initial total of 365 records. The research stages included data preprocessing, rainfall labeling into three categories (No Rain, Rain, and Extreme Rain), data splitting into training and testing sets, and classification using five machine learning algorithms. The results indicate that the Support Vector Machine (SVM) achieved the best performance, with an accuracy of 72,72%, precision of 74.58%, recall of 48.96%, and F1-score of 72.61%. Based on these findings, SVM is considered more effective than the other methods for classifying rainfall using meteorological data in Palembang.]]>
Copyrights © 2026
