Penerapan Machine Learning Extreme Gradient Boosting Dalam Klasifikasi Potensi Tsunami Berdasarkan Data Gempa Bumi
Kata Kunci:
tsunami, xgboost, SMOTE, grid-search, klasifikasiAbstrak
Tsunami merupakan bencana alam yang berdampak besar, khususnya di wilayah rawan seperti Indonesia. Penelitian ini bertujuan mengklasifikasikan potensi tsunami berdasarkan data gempa bumi menggunakan algoritma Extreme Gradient Boosting (XGBoost). Dataset mencakup data gempa dari 1900 hingga 2023 dengan total 1.376 data dan mengandung ketidakseimbangan kelas. Untuk mengatasi masalah ini, teknik Synthetic Minority Over-sampling Technique (SMOTE) diterapkan. Model dikembangkan dengan menyetel hyperparameter seperti max_depth, learning_rate, gamma, min_child_weight, colsample_bytree, dan subsample menggunakan Grid Search. Hasil pengujian menunjukkan bahwa kombinasi hyperparameter terbaik menghasilkan accuracy 85%, dengan recall, precision, dan F1-score masing-masing sebesar 0.74. Setelah penerapan SMOTE, accuracy menurun menjadi 84%, tetapi recall meningkat menjadi 0.79 dengan precision 0.71 dan F1-score 0.75. Evaluasi menggunakan metrik accuracy, precision, recall, dan F1-score menunjukkan bahwa penerapan SMOTE memberikan prediksi yang lebih baik untuk kelas tsunami. Pendekatan ini diharapkan berkontribusi dalam mitigasi bencana tsunami melalui sistem deteksi dini berbasis data gempa bumi.
Referensi
Cao, Q. et al., 2023. Comparative study of neonatal brain injury fetuses using machine learning methods for perinatal data. Computer Methods and Programs in Biomedicine, Volume 240, p. 107701.
Chimphlee, W. & Chimphlee, S., 2024. Hyperparameters optimization XGBoost for network intrusion detection using CSE-CIC-IDS 2018 dataset. IAES International Journal of Artificial Intelligence (IJ-AI), Volume 13, pp. 817- 826.
Han, Y., Wei, Z. & Huang, G., 2024. An imbalance data quality monitoring based on SMOTE XGBOOST supported by edge computing. Scientific Reports, 14(1).
Hasnol Yusri, H. I. et al., 2022. Water Quality Classification Using SVM And XGBoost Method. Shah Alam, IEEE 13th Control and System Graduate Research Colloquium (ICSGRC).
Montesinos-López, O., Montesinos, A. & Crossa, J., 2022. Multivariate Statistical Machine Learning Methods for Genomic Prediction. Cham: Springer.
Novianty, A. et al., 2019. Tsunami Potential Identification based on Seismic Features using KNN Algorithm. 2019 IEEE 7th Conference on Systems, Process and Control (ICSPC), pp. 155-160.
Pepinsky, T. B., 2018. A Note on Listwise Deletion versus Multiple Imputation. Political Analysis, Volume 26, p. 480–488.
Priyana, I. et al., 2024. Predictive Boosting for Employee Retention with SMOTE and XGBoost Hyperparameter Tuning. Surakarta, IEEE.
Reid, J. A. & Mooney, W. D., 2023. Tsunami Occurrence 1900–2020: A Global Review, with Examples from Indonesia. Pure and Applied Geophysics, 180(5), pp. 1549-1571.
Sun, Y. & Yang, G., 2019. Feature Engineering for Search Advertising Recognition. Qingdao, Nanjing, IEEE (Institute of Electrical and Electronics Engineers).
Yulianti, S., Soesanto, O. & Sukmawaty, Y., 2022. Penerapan Metode Extreme Gradient Boosting (XGBOOST) pada Klasifikasi Nasabah Kartu Kredit. Journal of Mathematics Theory and Application, 4(1), pp. 21-26.
Cao, Q. et al., 2023. Comparative study of neonatal brain injury fetuses using machine learning methods for perinatal data. Computer Methods and Programs in Biomedicine, Volume 240, p. 107701.
Chimphlee, W. & Chimphlee, S., 2024. Hyperparameters optimization XGBoost for network intrusion detection using CSE-CIC-IDS 2018 dataset. IAES International Journal of Artificial Intelligence (IJ-AI), Volume 13, pp. 817- 826.
Han, Y., Wei, Z. & Huang, G., 2024. An imbalance data quality monitoring based on SMOTE XGBOOST supported by edge computing. Scientific Reports, 14(1).
Hasnol Yusri, H. I. et al., 2022. Water Quality Classification Using SVM And XGBoost Method. Shah Alam, IEEE 13th Control and System Graduate Research Colloquium (ICSGRC).
Montesinos-López, O., Montesinos, A. & Crossa, J., 2022. Multivariate Statistical Machine Learning Methods for Genomic Prediction. Cham: Springer.
Novianty, A. et al., 2019. Tsunami Potential Identification based on Seismic Features using KNN Algorithm. 2019 IEEE 7th Conference on Systems, Process and Control (ICSPC), pp. 155-160.
Pepinsky, T. B., 2018. A Note on Listwise Deletion versus Multiple Imputation. Political Analysis, Volume 26, p. 480–488.
Priyana, I. et al., 2024. Predictive Boosting for Employee Retention with SMOTE and XGBoost Hyperparameter Tuning. Surakarta, IEEE.
Reid, J. A. & Mooney, W. D., 2023. Tsunami Occurrence 1900–2020: A Global Review, with Examples from Indonesia. Pure and Applied Geophysics, 180(5), pp. 1549-1571.
Sun, Y. & Yang, G., 2019. Feature Engineering for Search Advertising Recognition. Qingdao, Nanjing, IEEE (Institute of Electrical and Electronics Engineers).
Yulianti, S., Soesanto, O. & Sukmawaty, Y., 2022. Penerapan Metode Extreme Gradient Boosting (XGBOOST) pada Klasifikasi Nasabah Kartu Kredit. Journal of Mathematics Theory and Application, 4(1), pp. 21-26.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2025 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
