Rainfall Classification Based on El-Niño and La-Niña Climate Phenomenon Using Naive Bayes Classifier Algorithm

As a tropical country, Indonesia faces significant challenges due to global climate phenomena such as El Niño and La Niña that impact rainfall patterns. This research aims to classify daily rainfall in major Indonesian cities such as, DKI Jakarta, Surabaya, Medan, Makassar, and Bandung, into three main categories, namely moderate rain, extreme rain, and no rain. In addition, it identifies climate conditions based on El Niño, La Niña, and Normal categories by applying the Naïve Bayes Classifier algorithm. In this study, the CRISP-DM (Cross-Industry Standard Process for Data Mining) method was used as a framework for processing daily rainfall data for the period January to December 2023, obtained from BMKG. The analysis results show that the Naïve Bayes Classifier algorithm has high performance with 93.15% accuracy, 98% precision, 93% recall, and 94% F1-score. Further analysis, this study found that El Niño causes a significant decrease in rainfall, while La Niña increases extreme rainfall, especially in Makassar and Medan. This research contributes to the development of rainfall classification models that can help the government to anticipate the impacts of climate change and improve the efficiency of water resources management in urban areas.