Claim Missing Document
Check
Articles

Found 1 Documents
Search

ANALISIS FAKTOR DAN POLA KEJADIAN BANJIR DI BANDAR LAMPUNG MENGGUNAKAN ARIMA, RANDOM FOREST, DAN XGBOOST Suaif, Ahmad; Sylvianti Rahayu, Eka
Jurnal Teknologi Komputer dan Informatika Vol 3 No 2 (2025): Jurnal Teknologi Komputer dan Informatika (TEKOMIN)
Publisher : LPPM Politeknik Pajajaran ICB Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59820/tekomin.v3i2.339

Abstract

Flooding is a significant environmental problem in Bandar Lampung City, influenced by various factors such as rainfall, humidity, etc. This study aims to analyze the factors that contribute to flooding and build a prediction model for flood patterns. The methods used include factor analysis with Random Forest Classifier and prediction model using ARIMA, Random Forest Regressor, and XGBoost Regressor. The results show that rainfall is the dominant factor with a feature importance value of 0.49. From the results of the comparison of prediction models, XGBoost Regressor provides the best performance with an RMSE value of 0.88, From the results of the comparison of prediction models, XGBoost Regressor provides the best performance with an RMSE value of 0.88 and MAE of 0.75, as well as a positive R2 value of 0.11. The conclusion of this study confirms that the ensemble learning-based machine learning method is superior to statistical models in predicting flood events.