Optimasi Estimasi Intensitas Guncangan Gempa Skala MMI Menggunakan XGBoost Berdasarkan Parameter Seismik dan GMPE
DOI:
https://doi.org/10.57235/jetish.v5i2.8966Keywords:
Intensitas Guncangan Gempa, Modified Mercalli Intensity (MMI), XGBoost, Ground Motion Prediction Equations (GMPE), Physics-Informed Machine LearningAbstract
Indonesia merupakan wilayah dengan aktivitas seismik tinggi sehingga estimasi intensitas guncangan gempa yang akurat menjadi komponen penting dalam mitigasi bencana. Persamaan empiris Ground Motion Prediction Equations (GMPE) banyak digunakan untuk mengestimasi intensitas guncangan, namun memiliki keterbatasan dalam merepresentasikan hubungan nonlinier antara parameter seismik dan kondisi lokal. Penelitian ini bertujuan mengembangkan model estimasi Modified Mercalli Intensity (MMI) berbasis physics-informed machine learning dengan mengombinasikan algoritma XGBoost dan GMPE. Dataset yang digunakan berasal dari arsip USGS ShakeMap wilayah Indonesia periode 2004–2025 yang mencakup 528 kejadian gempa dan 6.222 rekaman observasi. Tahapan penelitian meliputi pra-pemrosesan data, rekayasa fitur, perhitungan estimasi awal menggunakan GMPE, pelatihan model XGBoost, serta evaluasi menggunakan Group K-Fold Cross Validation melalui studi ablasi. Hasil penelitian menunjukkan bahwa model hibrida mampu mengatasi keterbatasan model machine learning murni sekaligus mempertahankan stabilitas pendekatan empiris. Model menghasilkan nilai Mean Absolute Error (MAE) 0,435 skala MMI, dengan prediksi GMPE sebagai fitur paling dominan berdasarkan analisis feature importance. Model terbaik selanjutnya diimplementasikan ke dalam prototipe berbasis ONNX yang mampu melakukan estimasi intensitas guncangan secara real-time. Hasil penelitian menunjukkan bahwa pendekatan hibrida berpotensi mendukung sistem peringatan dini dan pengambilan keputusan dalam mitigasi bencana gempa bumi.
Downloads
References
Allen, T. I., & Wald, D. J. (2009). On the Use of High-Resolution Topographic Data as a Proxy for Seismic Site Conditions (VS30). Bulletin of the Seismological Society of America, 99(2A), 935–943.
Asim, K. M., Idris, A., Iqbal, T., & Martínez-Álvarez, F. (2018). Earthquake prediction model using support vector regressor and hybrid neural networks. PLOS ONE, 13(7).
Boore, D. M., & Atkinson, G. M. (2008). Ground-Motion Prediction Equations for the Average Horizontal Component of PGA, PGV, and 5%-Damped PSA at Spectral Periods between 0.01 s and 10.0 s. Earthquake Spectra, 24(1), 99–138.
Caprio, M., Bernadetta Tarigan, Worden, C. B., Wiemer, S., & Wald, D. J. (2015). Ground Motion to Intensity Conversion Equations (GMICEs): A Global Relationship and Evaluation of Regional Dependency. 105(3), 1476–1490.
Chen, T., & Guestrin, C. (2016). XGBoost: a Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD ’16, 1(1), 785–794.
Chiou, B. S. J., & Youngs, R. R. (2014). Update of the Chiou and Youngs NGA Model for the Average Horizontal Component of Peak Ground Motion and Response Spectra. Earthquake Spectra, 1117–1153.
Derras, B., Bard, P. Y., & Cotton, F. (2013). Towards fully data driven ground-motion prediction models for Europe. Bulletin of Earthquake Engineering, 12(1), 495–516.
Kong, Q., Trugman, D. T., Ross, Z. E., Bianco, M. J., Meade, B. J., & Gerstoft, P. (2018). Machine Learning in Seismology: Turning Data into Insights. Seismological Research Letters. 90(1), 3–14.
Mignan, A., & Broccardo, M. (2020). Neural Network Applications in Earthquake Prediction (1994–2019): Meta-Analytic and Statistical Insights on Their Limitations. Seismological Research Letters, 91(4), 2330–2342.
Musson, R. M. W., Grünthal, G., & Stucchi, M. (2009). The comparison of macroseismic intensity scales. Journal of Seismology, 14(2), 413–428.
Natawidjaja, D. H. (2007). The Sumatran Fault Zone—from Source to Hazard. Journal of Earthquake and Tsunami.
New Publications. (2004). Seismological Research Letters. 75(6), 752–753.
Pusat Studi Gempa Nasional. (2017). Peta sumber dan bahaya gempa Indonesia tahun 2017.
S. Mostafa Mousavi, & Beroza, G. C. (2022). Machine Learning in Earthquake Seismology. 51(1).
Wald, D. J., Quitoriano, V., Heaton, T. H., & Kanamori, H. (1999). Relationships between Peak Ground Acceleration, Peak Ground Velocity, and Modified Mercalli Intensity in California. Earthquake Spectra, 15(3), 557–564.
Wood, H. O., & Neumann, F. (1931). Modified Mercalli intensity scale of 1931. Modified Mercalli Intensity Scale of 1931, 21(4), 277–283.
Worden, C. B., Gerstenberger, M. C., Rhoades, D. A., & Wald, D. J. (2012). Probabilistic Relationships between Ground-Motion Parameters and Modified Mercalli Intensity in California. Bulletin of the Seismological Society of America, 102(1), 204–221.
Wyss, M. (1997). Cannot Earthquakes Be Predicted? Science. 278(5337), 487–490.
Downloads
Published
Issue
Section
Citation Check
License
Copyright (c) 2026 Felix John Pardamean Hutabarat, Ayman Human Sukma, Azhara Amelia H, Rinto Manik, Sehati Saurmatania Tampubolon, Suvriadi Panggabean
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors are copyright holders and maintain author rights in accordance with the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) or comparable license. While holding these rights, authors grant the JETISH: Journal of Education Technology Information Social Sciences and Health (publisher of JETISH) a non-exclusive right to the first publication of their articles, including abstracts. This enables us to ensure full copyright protection and to disseminate the article to the widest possible readership in electronic format. Authors are themselves responsible for obtaining permission to reproduce copyright material from other sources.
