<![CDATA[AbstractIndonesia faces high tsunami risk due to its position on the Pacific Ring of Fire. This study analyzes machine learning implementation using PyCaret AutoML framework for tsunami prediction based on earthquake parameters. The dataset consists of 782 earthquake records with 13 features. Methodology includes automated preprocessing with outlier removal (16.88%), 80:20 train-test split, 10-fold cross-validation, and comprehensive evaluation. Results show XGBoost achieved best performance (93.95% accuracy, 97.19% AUC, 90.89% F1-score), LightGBM highest AUC (97.35%), Random Forest highest recall (93.11%), and SVM lowest performance (75.81% accuracy). Detailed analysis of PyCaret's automated workflow validates ensemble boosting superiority for tsunami early warning systems in Indonesia.Keywords: tsunami, machine learning, PyCaret, XGBoost, early warningAbstrakIndonesia menghadapi risiko tsunami tinggi karena posisinya di jalur Cincin Api Pasifik. Penelitian ini menganalisis implementasi machine learning menggunakan framework PyCaret AutoML untuk prediksi tsunami berdasarkan parameter gempa bumi. Dataset terdiri dari 782 rekaman gempa dengan 13 fitur. Metodologi mencakup preprocessing otomatis dengan penghapusan outlier (16,88%), pembagian data 80:20, cross-validation 10-fold, dan evaluasi komprehensif. Hasil menunjukkan XGBoost mencapai performa terbaik (akurasi 93,95%, AUC 97,19%, F1-score 90,89%), LightGBM AUC tertinggi (97,35%), Random Forest recall tertinggi (93,11%), dan SVM performa terendah (akurasi 75,81%). Analisis detail workflow otomatis PyCaret memvalidasi keunggulan ensemble boosting untuk sistem peringatan dini tsunami di Indonesia.Kata Kunci: tsunami, machine learning, PyCaret, XGBoost, peringatan dini ]]>
Copyrights © 2026
