Analisis Perbandingan Model Regresi Linier dan XGBoost untuk Mengkaji Dampak ENSO terhadap Curah Hujan di Kota Ternate Tahun 2023

Amra, Firman Almaliky Gapri
Widodo, Anton
Nugraha, Muchamad Rizqy

Journal of Computation Physics and Earth Science
Vol 5 No 1 (2025): Journal of Computation Physics and Earth Science

The purpose of this study is to evaluate how well two prediction models—linear regression and XGBoost—perform in assessing how ENSO (El Niño-Southern Oscillation) affects rainfall in Ternate City in 2023. The Meteorology, Climatology, and Geophysics Agency (BMKG) provided monthly rainfall data, while the Bureau of Meteorology (BOM) in Australia provided ENSO index data. Performance indicators such Pearson correlation analysis, the coefficient of determination (R-squared), and mean squared error (MSE) were used in the evaluation. According to the findings, the two models perform differently when it comes to capturing the pattern of the link between rainfall and ENSO; XGBoost is more adaptable but has a tendency to overfit on small amounts of data, whereas linear regression obtains a better R-squared value.