Prediksi Magnitudo Gempa Menggunakan Random Forest, Support Vector Regression, XGBoost, LightGBM, dan Multi-Layer Perceptron Berdasarkan Data Kedalaman dan Geolokasi
DOI:
https://doi.org/10.52436/1.jpti.470Kata Kunci:
lightgbm, multi-layer perceptron, prediksi gempa, random forest, support vector regression, xgboostAbstrak
Penelitian ini bertujuan membandingkan kinerja lima algoritma pembelajaran mesin, yaitu Random Forest, Support Vector Regression, XGBoost, LightGBM, dan Multi-Layer Perceptron dalam memprediksi magnitudo gempa berdasarkan data kedalaman dan geolokasi. Masalah yang diangkat adalah pentingnya prediksi magnitudo gempa yang lebih akurat untuk meningkatkan efektivitas mitigasi risiko bencana, terutama di daerah rawan gempa. Data yang digunakan mencakup informasi kedalaman, lintang, dan bujur dari peristiwa gempa selama periode tertentu. Metode penelitian melibatkan pembagian data pelatihan dan pengujian, serta evaluasi kinerja model menggunakan metrik Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), dan R². Hasil penelitian menunjukkan bahwa LightGBM memberikan performa terbaik dengan nilai MAE sebesar 0,4688, RMSE sebesar 0,6284, dan R² sebesar 0,2458. Random Forest mengikuti dengan nilai MAE sebesar 0,4750, RMSE sebesar 0,6312, dan R² sebesar 0,2391. XGBoost menunjukkan performa yang kompetitif dengan MAE sebesar 0,4932, RMSE sebesar 0,6471, dan R² sebesar 0,2003. Sebaliknya, Support Vector Regression mencatatkan nilai MAE sebesar 0,5136, RMSE sebesar 0,6987, dan R² sebesar 0,0677, sementara Multi-Layer Perceptron memberikan kinerja terendah dengan MAE sebesar 0,5190, RMSE sebesar 0,7152, dan R² sebesar 0,0231. Dampak penelitian ini sangat penting bagi pengembangan sistem peringatan dini gempa dan peningkatan akurasi prediksi magnitudo gempa. Penelitian ini menegaskan bahwa pemilihan model yang tepat dapat berkontribusi pada mitigasi risiko bencana, dengan memberikan informasi yang lebih akurat mengenai kekuatan gempa yang dapat terjadi. Temuan ini juga menunjukkan bahwa algoritma pembelajaran mesin, terutama LightGBM dan Random Forest, dapat menjadi alat yang efektif dalam analisis seismologi dan aplikasi prediksi gempa.
Unduhan
Referensi
Z. Zhao dkk., “A Seismic Emergency Performance Optimization Model for Infrastructure Systems Under Demand Differences: A Case Study in China,” Earthq. Eng. Resil., vol. 1, no. 2, hlm. 196–210, 2022, doi: 10.1002/eer2.22.
J. Chu, Q. Zhang, W. Ai, dan H. Yu, “A Hybrid Intelligent Model for Urban Seismic Risk Assessment From the Perspective of Possibility and Vulnerability Based on Particle Swarm Optimization,” Sci. Program., vol. 2021, hlm. 1–16, 2021, doi: 10.1155/2021/2218044.
Z. A. Lamjiry dan R. Gifford, “Earthquake Threat! Understanding the Intention to Prepare for the Big One,” Risk Anal., vol. 42, no. 3, hlm. 487–505, 2021, doi: 10.1111/risa.13775.
R. Ternero, “Analysis of Pedestrian Behavior for the Optimization of Evacuation Plans in Tall Buildings: Case Study Santiago, Chile,” Buildings, vol. 13, no. 12, hlm. 2907, 2023, doi: 10.3390/buildings13122907.
V. Scapini, “Disaster, Infrastructure Damage, and Health,” Int. J. Saf. Secur. Eng., vol. 10, no. 2, hlm. 219–225, 2020, doi: 10.18280/ijsse.100208.
D. B. d. Freitas, G. S. França, T. M. Scherrer, C. S. Vilar, dan R. Silva, “Investigating the Signatures of Long-Range Persistence in Seismic Sequences Along Circum-Pacific Subduction Zones,” Braz. J. Geophys., vol. 37, no. 4, hlm. 409, 2019, doi: 10.22564/rbgf.v37i4.2018.
V. Scapini dan E. Zuñiga, “A Markov Chain Approach to Model Reconstruction,” Int. J. Comput. Methods Exp. Meas., vol. 8, no. 4, hlm. 316–325, 2020, doi: 10.2495/cmem-v8-n4-316-325.
T. Wang, J. Zhuang, dan T. Kato, “Assessing the Potential Improvement in Short?term Earthquake Forecasts From Incorporation of GPS Data,” Geophys. Res. Lett., vol. 40, no. 11, hlm. 2631–2635, 2013, doi: 10.1002/grl.50554.
D. Schorlemmer dkk., “The Collaboratory for the Study of Earthquake Predictability: Achievements and Priorities,” Seismol. Res. Lett., vol. 89, no. 4, hlm. 1305–1313, 2018, doi: 10.1785/0220180053.
J. Woessner dkk., “A Retrospective Comparative Forecast Test on the 1992 Landers Sequence,” J. Geophys. Res. Atmospheres, vol. 116, no. B5, 2011, doi: 10.1029/2010jb007846.
M. T. Page, D. Alderson, dan J. Doyle, “The Magnitude Distribution of Earthquakes Near Southern California Faults,” J. Geophys. Res. Atmospheres, vol. 116, no. B12, 2011, doi: 10.1029/2010jb007933.
A. Akinci, “HAZGRIDX: Earthquake Forecasting Model for ML? 5.0 Earthquakes in Italy Based on Spatially Smoothed Seismicity,” Ann. Geophys., vol. 53, no. 3, 2010, doi: 10.4401/ag-4811.
A. Heuret, S. Lallemand, F. Funiciello, C. Piromallo, dan C. Faccenna, “Physical Characteristics of Subduction Interface Type Seismogenic Zones Revisited,” Geochem. Geophys. Geosystems, vol. 12, no. 1, hlm. n/a-n/a, 2011, doi: 10.1029/2010gc003230.
A. Plesch dkk., “Community Fault Model (CFM) for Southern California,” Bull. Seismol. Soc. Am., vol. 97, no. 6, hlm. 1793–1802, 2007, doi: 10.1785/0120050211.
R. Tehseen, M. S. Farooq, dan A. Abid, “Earthquake Prediction Using Expert Systems: A Systematic Mapping Study,” Sustainability, vol. 12, no. 6, hlm. 2420, 2020, doi: 10.3390/su12062420.
X. Lu, “Machine Learning-Based Precursor Detection Using Seismic Multi-Parameter Data,” Appl. Sci., vol. 14, no. 6, hlm. 2401, 2024, doi: 10.3390/app14062401.
N. B. Jarah, A. H. H. Alasadi, dan K. M. Hashim, “Earthquake Prediction Technique: A Comparative Study,” Iaes Int. J. Artif. Intell. Ij-Ai, vol. 12, no. 3, hlm. 1026, 2023, doi: 10.11591/ijai.v12.i3.pp1026-1032.
Z. Li, M. Meier, E. Hauksson, Z. Zhan, dan J. Andrews, “Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning,” Geophys. Res. Lett., vol. 45, no. 10, hlm. 4773–4779, 2018, doi: 10.1029/2018gl077870.
F. Corbi, J. Bedford, L. Sandri, F. Funiciello, A. Gualandi, dan M. Rosenau, “Predicting Imminence of Analog Megathrust Earthquakes With Machine Learning: Implications for Monitoring Subduction Zones,” Geophys. Res. Lett., vol. 47, no. 7, 2020, doi: 10.1029/2019gl086615.
L. Izquierdo-Horna, J. Zevallos, dan Y. YEPEZ, “An Integrated Approach to Seismic Risk Assessment Using Random Forest and Hierarchical Analysis: Pisco, Peru,” Heliyon, vol. 8, no. 10, hlm. e10926, 2022, doi: 10.1016/j.heliyon.2022.e10926.
F. Provost, C. Hibert, dan J. Malet, “Automatic Classification of Endogenous Landslide Seismicity Using the Random Forest Supervised Classifier,” Geophys. Res. Lett., vol. 44, no. 1, hlm. 113–120, 2017, doi: 10.1002/2016gl070709.
K. M. Asim, A. Idris, T. Iqbal, dan F. Martínez?Álvarez, “Earthquake Prediction Model Using Support Vector Regressor and Hybrid Neural Networks,” Plos One, vol. 13, no. 7, hlm. e0199004, 2018, doi: 10.1371/journal.pone.0199004.
J. Yin, “A Semismooth Newton Method for Support Vector Classification and Regression,” Comput. Optim. Appl., vol. 73, no. 2, hlm. 477–508, 2019, doi: 10.1007/s10589-019-00075-z.
M. Sinambela, M. Situmorang, K. Tarigan, S. Humaidi, dan M. Sirait, “Waveforms Classification of Northern Sumatera Earthquakes for New Mini Region Stations Using Support Vector Machine,” Int. J. Adv. Sci. Eng. Inf. Technol., vol. 11, no. 2, hlm. 489–494, 2021, doi: 10.18517/ijaseit.11.2.12503.
“Technical Bottlenecks and Future Trends in Earthquake Prediction,” Environ. Resour. Ecol. J., vol. 8, no. 1, 2024, doi: 10.23977/erej.2024.080118.
“LUTanh Activation Function to Optimize BI-LSTM in Earthquake Forecasting,” Int. J. Intell. Eng. Syst., vol. 17, no. 1, hlm. 572–583, 2024, doi: 10.22266/ijies2024.0229.48.
O. N. Akarsu, “A Bibliometric Review of Earthquake and Machine Learning Research,” Civ. Eng. Limits, vol. 5, no. 1, hlm. 1–10, 2024, doi: 10.36937/cebel.2024.1908.
S. Tsuno, “Application of the on-Site P-Wave Earthquake Early Warning Method Based on Site-Specific Ratios of S-Waves to P-Waves to the 2016 Kumamoto Earthquake Sequence, Japan,” Earth Planets Space, vol. 76, no. 1, 2024, doi: 10.1186/s40623-024-01968-y.
S. Iai dan K. Ichii, “Soils and Foundations During Earthquakes,” Soils Found., vol. 50, no. 6, hlm. 937–953, 2010, doi: 10.3208/sandf.50.937.
M. C. Porcu, J. C. Vielma, G. Pais, D. O. Bravo, dan J. C. V. Quintero, “Some Issues in the Seismic Assessment of Shear-Wall Buildings Through Code-Compliant Dynamic Analyses,” Buildings, vol. 12, no. 5, hlm. 694, 2022, doi: 10.3390/buildings12050694.
T. Moriya, T. Mogi, dan M. Takada, “Anomalous Pre-Seismic Transmission of VHF-band Radio Waves Resulting From Large Earthquakes, and Its Statistical Relationship to Magnitude of Impending Earthquakes,” Geophys. J. Int., vol. 180, no. 2, hlm. 858–870, 2010, doi: 10.1111/j.1365-246x.2009.04461.x.
G. Cremen dan C. Galasso, “Earthquake Early Warning: Recent Advances and Perspectives,” Earth-Sci. Rev., vol. 205, hlm. 103184, 2020, doi: 10.1016/j.earscirev.2020.103184.
X. Wang dkk., “Small Earthquakes Can Help Predict Large Earthquakes: A Machine Learning Perspective,” Appl. Sci., vol. 13, no. 11, hlm. 6424, 2023, doi: 10.3390/app13116424.
N. Guo dkk., “Using Improved Support Vector Regression to Predict the Transmitted Energy Consumption Data by Distributed Wireless Sensor Network,” Eurasip J. Wirel. Commun. Netw., vol. 2020, no. 1, 2020, doi: 10.1186/s13638-020-01729-x.
G. C. Beroza, M. Segou, dan S. M. Mousavi, “Machine Learning and Earthquake Forecasting—next Steps,” Nat. Commun., vol. 12, no. 1, 2021, doi: 10.1038/s41467-021-24952-6.
