PEMODELAN NILAI B-VALUE UNTUK MITIGASI RISIKO GEMPA DI ZONA MEGATHRUST SELATAN JAWA MENGGUNAKAN LSTM, SVM, DAN RANDOM FOREST

Ismi Amalia; Taswanda Taryo; Sudarno  Wiharjo

doi:10.31539/apcvbd82

Authors

Ismi Amalia Universitas Pamulang, Tangerang Selatan
Taswanda Taryo Universitas Pamulang, Tangerang Selatan
Sudarno Wiharjo Universitas Pamulang, Tangerang Selatan

DOI:

https://doi.org/10.31539/apcvbd82

Abstract

Zona Megathrust Selatan Jawa merupakan wilayah subduksi aktif dengan tingkat kegempaan tinggi yang rawan terhadap bencana gempa bumi besar dan tsunami, di mana parameter b-value bertindak sebagai indikator kritis dalam memetakan akumulasi tegangan tektonik. Penelitian ini bertujuan memodelkan dinamika deret waktu b-value secara spasio-temporal menggunakan metode Maximum Likelihood Estimation (MLE) yang dikombinasikan dengan teknik pemulusan jendela bergerak serta tiga pendekatan kecerdasan buatan, yaitu Long Short-Term Memory (LSTM), Support Vector Machine (SVM/SVR), dan Random Forest (RF). Hasil evaluasi menunjukkan bahwa pada konfigurasi standar, pendekatan SVM memberikan akurasi numerik terbaik karena ketangguhannya mengolah dataset berukuran sedang tanpa gejala overfitting, disusul oleh efisiensi model RF, meskipun keduanya menunjukkan keterbatasan berupa gejala perkiraan malas (lazy prediction) atau penundaan fase waktu. Sebaliknya, superioritas arsitektural sekuensial yang sesungguhnya berhasil dicapai oleh jaringan LSTM pada skenario eksperimen kontrol berbasis masukan data seketika, di mana pemotongan rantai historis jangka panjang mampu membebaskan model dari bias inersia temporal sehingga mekanisme gerbang pengaturnya bekerja jauh lebih responsif, adaptif, dan presisi dalam melacak kausalitas perubahan stres tektonik tanpa penundaan fase naif.

References

Buku

Pusat Studi Gempa Nasional (PuSGeN) (2025). Peta sumber dan bahaya gempa Indonesia tahun 2024. Kementerian Pekerjaan Umum

Jurnal Ilmiah

5. Spatial–temporal variations of b‑values prior.pdf. (n.d.).

Arubi, D., Zulfakriza, Rosalia, S., Sahara, D. P., & Puspito, N. T. (2022). Estimation of B-Value Variation as Earthquake Precursor in Java Region with Maximum Likelihood Method. IOP Conference Series: Earth and Environmental Science, 1047(1). https://doi.org/10.1088/1755-1315/1047/1/012027

Barrera-Animas, A. Y., Oyedele, L. O., Bilal, M., Akinosho, T. D., Delgado, J. M. D., & Akanbi, L. A. (2022). Rainfall prediction: A comparative analysis of modern machine learning algorithms for time-series forecasting. Machine Learning with Applications, 7(October 2021), 100204. https://doi.org/10.1016/j.mlwa.2021.100204

Chan, C. H., Wu, Y. M., Tseng, T. L., Lin, T. L., & Chen, C. C. (2012). Spatial and temporal evolution of b-values before large earthquakes in Taiwan. Tectonophysics, 532–535, 215–222. https://doi.org/10.1016/j.tecto.2012.02.004

Domel, P., Hibert, C., Schlindwein, V., & Plaza-Faverola, A. (2023). Event recognition in marine seismological data using Random Forest machine learning classifier. Geophysical Journal International, 235(1), 589–609. https://doi.org/10.1093/gji/ggad244

Geffers, G. M., Main, I. G., & Naylor, M. (2022). Biases in estimating b-values from small earthquake catalogues: How high are high b-values. Geophysical Journal International, 229(3), 1840–1855. https://doi.org/10.1093/gji/ggac028

Hamdi, A. H. Al, Nugroho, H. A., & Kusumoputro, B. (2024). Comparative Analysis of LSTM and Bi-LSTM Models for Earthquake Occurrence Prediction in Tokai-Japan Region. International Journal of Electrical, Computer, and Biomedical Engineering, 2(4), 500–511. https://doi.org/10.62146/ijecbe.v2i4.87

Huang, F., Xiong, H., Chen, S., Lv, Z., Huang, J., Chang, Z., & Catani, F. (2023). Slope stability prediction based on a long short-term memory neural network: comparisons with convolutional neural networks, support vector machines and random forest models. International Journal of Coal Science and Technology, 10(1). https://doi.org/10.1007/s40789-023-00579-4

Hutchings, S. J., & Mooney, W. D. (2021). The Seismicity of Indonesia and Tectonic Implications. Geochemistry, Geophysics, Geosystems, 22(9), 1–42. https://doi.org/10.1029/2021GC009812

Janzakovna, R. M. (2025). International Journal of Artificial Intelligence & Applications (IJAIA). International Journal of Artificial Intelligence, 5(2), 1499–1504. http://www.airccse.org/journal/ijaia/ijaia

Jiang, C., Han, L., Long, F., Lai, G., Yin, F., Bi, J., & Si, Z. (2021). Spatiotemporal heterogeneity of b values revealed by a data-driven approach for the 17 June 2019 MS6.0 Changning earthquake sequence, Sichuan, China. Natural Hazards and Earth System Sciences, 21(7), 2233–2244. https://doi.org/10.5194/nhess-21-2233-2021

Kamal, M., Zhang, B., Cao, J., Zhang, X., & Chang, J. (2022). Comparative Study of Artificial Neural Network and Random Forest Model for Susceptibility Assessment of Landslides Induced by Earthquake in the Western Sichuan Plateau, China. Sustainability (Switzerland), 14(21). https://doi.org/10.3390/su142113739

Kubo, H., Naoi, M., & Kano, M. (2024). Recent advances in earthquake seismology using machine learning. Earth, Planets and Space, 76(1). https://doi.org/10.1186/s40623-024-01982-0

Lacidogna, G., Borla, O., & De Marchi, V. (2023). Statistical Seismic Analysis by b-Value and Occurrence Time of the Latest Earthquakes in Italy. Remote Sensing, 15(21). https://doi.org/10.3390/rs15215236

Mamo, D. N., Walle, A. D., Woldekidan, E. K., Adem, J. B., Gebremariam, Y. H., Alemayehu, M. A., Enyew, E. B., & Kebede, S. D. (2025). Performance evaluation and comparative analysis of different machine learning algorithms in predicting postnatal care utilization: Evidence from the ethiopian demographic and health survey 2016. PLOS Digital Health, 4(1), 1–25. https://doi.org/10.1371/journal.pdig.0000707

Nanjo, K. Z., & Yoshida, A. (2017). Anomalous decrease in relatively large shocks and increase in the p and b values preceding the April 16, 2016, M7.3 earthquake in Kumamoto, Japan. Earth, Planets and Space, 69(1). https://doi.org/10.1186/s40623-017-0598-2

R, S. R., & Madrinovella, I. (2024). Spatial and Temporal B-Value Analysis of the Yogyakarta Region Using Earthquake Data 1960 – 2024. JGE (Jurnal Geofisika Eksplorasi), 10(3), 191–203. https://doi.org/10.23960/jge.v10i3.468

Sadhukhan, B., Chakraborty, S., Mukherjee, S., & Samanta, R. K. (2023). Climatic and seismic data-driven deep learning model for earthquake magnitude prediction. Frontiers in Earth Science, 11(February), 1–24. https://doi.org/10.3389/feart.2023.1082832

Supendi, P., Widiyantoro, S., Rawlinson, N., Yatimantoro, T., Muhari, A., Hanifa, N. R., Gunawan, E., Shiddiqi, H. A., Imran, I., Anugrah, S. D., Daryono, D., Prayitno, B. S., Adi, S. P., Karnawati, D., Faizal, L., & Damanik, R. (2023). On the potential for megathrust earthquakes and tsunamis off the southern coast of West Java and southeast Sumatra, Indonesia. Natural Hazards, 116(1), 1315–1328. https://doi.org/10.1007/s11069-022-05696-y

Taroni, M., Vocalelli, G., & De Polis, A. (2021). Gutenberg–Richter B-Value Time Series Forecasting: A Weighted Likelihood Approach. Forecasting, 3(3), 561–569. https://doi.org/10.3390/forecast3030035

Turino, T., Saputro, R. E., & Karyono, G. (2025). Comparative Analysis of Decision Tree, Random Forest, Svm, and Neural Network Models for Predicting Earthquake Magnitude. Jurnal Teknik Informatika (Jutif), 6(2), 755–774. https://doi.org/10.52436/1.jutif.2025.6.2.2378

Utku, A., & Akcayol, M. A. (2024). Hybrid Deep Learning Model for Earthquake Time Prediction. Gazi University Journal of Science, 37(3), 1172–1188. https://doi.org/10.35378/gujs.1364529

Widiyantoro, S., Gunawan, E., Muhari, A., Rawlinson, N., Mori, J., Hanifa, N. R., Susilo, S., Supendi, P., Shiddiqi, H. A., Nugraha, A. D., & Putra, H. E. (2020). Implications for megathrust earthquakes and tsunamis from seismic gaps south of Java Indonesia. Scientific Reports, 10(1), 1–11. https://doi.org/10.1038/s41598-020-72142-z