Comparison of ARIMA, LSTM and GRU Models for Seismic b-Value Prediction in Southern Sumatera
DOI:
https://doi.org/10.30871/jaic.v10i3.12910Keywords:
ARIMA, b-value, earthquake, GRU, LSTMAbstract
Indonesia experiences high seismic activity due to its location at the convergence of three major tectonic plates, making continuous monitoring of earthquake potential crucial. A fundamental parameter in seismic hazard analysis is the b-value, which reflects the stress conditions, structural heterogeneity, and magnitude distribution within the Earth’s crust. Predicting b-value fluctuations remains challenging due to its highly volatile nature. This study aims to analyze and forecast the seismic b-value in Southern Sumatra by comparing a classical statistical model, ARIMA , with two advanced machine learning architectures, LSTM and GRU. Historical earthquake catalogs from BMKG and NEIC-USGS spanning 1960–2025 were utilized. The data underwent a declustering process using the Reasenberg method to eliminate foreshocks and aftershocks, yielding 15,844 independent events. The monthly b-value was then calculated using Maximum Likelihood Estimation. Furthermore, PSO was applied to tune the hyperparameters of the deep learning models. Evaluation reveals that ARIMA yields the highest predictive accuracy, achieving a Mean Absolute Error (MAE) of 0.11, Root Mean Square Error (RMSE) of 0.16, and Mean Absolute Percentage Error (MAPE) of 13.85%. In contrast, GRU (MAPE 14.30%) and LSTM (MAPE 16.22%) produced smoother predictions but struggled to capture extreme short-term fluctuations. The findings conclude that for volatile and limited-size time series data like regional b-values, the linear approach of ARIMA remains significantly more effective than complex deep learning models.
Downloads
References
[1] B. Rahmat, F. Afiadi, and E. Joelianto, “Earthquake Prediction System using Neuro-Fuzzy and Extreme Learning Machine,” in Proceedings of the International Conference on Science and Technology (ICST 2018), Paris, France: Atlantis Press, 2018. doi: 10.2991/icst-18.2018.95.
[2] Y. Wang, S. Li, and J. Song, “Exploring Magnitude Estimation for Earthquake Early Warning Using Available P-Wave Time Windows Based on Chinese Strong-Motion Records,” Pure Appl. Geophys., vol. 179, no. 11, pp. 4037–4052, Nov. 2022, doi: 10.1007/s00024-022-03062-4.
[3] R. Ito and Y. Kaneko, “Physical Mechanism for a Temporal Decrease of the Gutenberg‐Richter b ‐Value Prior to a Large Earthquake,” J. Geophys. Res. Solid Earth, vol. 128, no. 12, Dec. 2023, doi: 10.1029/2023JB027413.
[4] G. Lacidogna, O. Borla, and V. De Marchi, “Statistical Seismic Analysis by b-Value and Occurrence Time of the Latest Earthquakes in Italy,” Remote Sens. (Basel)., vol. 15, no. 21, p. 5236, Nov. 2023, doi: 10.3390/rs15215236.
[5] M. A. Bilal, Y. Ji, Y. Wang, M. P. Akhter, and M. Yaqub, “An Early Warning System for Earthquake Prediction from Seismic Data Using Batch Normalized Graph Convolutional Neural Network with Attention Mechanism (BNGCNNATT),” Sensors, vol. 22, no. 17, p. 6482, Aug. 2022, doi: 10.3390/s22176482.
[6] B. Rahmat et al., “Comparison of B-Value Predictions as Earthquake Precursors using Extreme Learning Machine and Deep Learning,” Internetworking Indonesia Journal, vol. 12, no. 1, pp. 47–52, 2020.
[7] C. H. Scholz, “On the stress dependence of the earthquake b-value,” Geophys. Res. Lett., vol. 42, no. 5, pp. 1399–1402, Mar. 2015, doi: 10.1002/2014GL062863.
[8] K. Lee, J. Oh, H. Lee, and K. You, “Earthquake Magnitude Estimation Using a Total Noise Enhanced Optimization Model,” Sensors, vol. 19, no. 6, p. 1454, Mar. 2019, doi: 10.3390/s19061454.
[9] K. Arvanitakis, I. Karydis, K. L. Kermanidis, and M. Avlonitis, “A machine learning approach for asperities’ location identification,” Evolving Systems, vol. 10, no. 1, pp. 41–50, Mar. 2019, doi: 10.1007/s12530-017-9204-x.
[10] J. B. Rundle, A. Donnellan, G. Fox, and J. P. Crutchfield, “Nowcasting Earthquakes by Visualizing the Earthquake Cycle with Machine Learning: A Comparison of Two Methods,” Surv. Geophys., vol. 43, no. 2, pp. 483–501, Apr. 2022, doi: 10.1007/s10712-021-09655-3.
[11] S. M. Mousavi and G. C. Beroza, “A Machine‐Learning Approach for Earthquake Magnitude Estimation,” Geophys. Res. Lett., vol. 47, no. 1, Jan. 2020, doi: 10.1029/2019GL085976.
[12] B. H. Mustawinar, K. Kardiana, Y. Yuliani, and D. R. Arifanti, “Peramalan Cadangan Devisa Menggunakan Metode Double Smoothing Exponential dan Metode Fuzzy Time Series,” Venn: Journal of Sustainable Innovation on Education, Mathematics and Natural Sciences, vol. 3, no. 3, pp. 105–114, Aug. 2024, doi: 10.53696/venn.v3i3.79.
[13] A. P. Meriani and A. Rahmatulloh, “Perbandingan Gated Recurrent Unit (GRU) Dan Algoritma Long Short Term Memory (LSTM) Linear Refression Dalam Prediksi Harga Emas Menggunakan Model Time Series,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 1, Jan. 2024, doi: 10.23960/jitet.v12i1.3808.
[14] R. E. Abercrombie, “Resolution and uncertainties in estimates of earthquake stress drop and energy release,” Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 379, no. 2196, p. 20200131, May 2021, doi: 10.1098/rsta.2020.0131.
[15] M. S. Abdalzaher, M. Krichen, and F. Falcone, “Emerging technologies and supporting tools for earthquake disaster management: A perspective, challenges, and future directions,” Progress in Disaster Science, vol. 23, p. 100347, Oct. 2024, doi: 10.1016/j.pdisas.2024.100347.
[16] C. JIANG, L. FANG, L. FAN, and B. LI, “Comparison of the earthquake detection effects of phaseNet and EQTransformer considering the Yangbi and Maduo Earthquakes,” Earthquake Science, vol. 34, no. 0, pp. 20210038–20210038, 2021, doi: 10.29382/Q20210038.
[17] Y. Zhong and Y. J. Tan, “Deep‐Learning‐Based Phase Picking for Volcano‐Tectonic and Long‐Period Earthquakes,” Geophys. Res. Lett., vol. 51, no. 12, Jun. 2024, doi: 10.1029/2024GL108438.
[18] G. Cremen and C. Galasso, “Earthquake early warning: Recent advances and perspectives,” Earth. Sci. Rev., vol. 205, p. 103184, Jun. 2020, doi: 10.1016/j.earscirev.2020.103184.
[19] F. Rachim, T. Tarno, and S. Sugito, “Perbandingan Fuzzy Time Series Dengan Metode Chen Dan Metode S. R. Singh (Studi Kasus : Nilai Impor di Jawa Tengah Periode Januari 2014 – Desember 2019),” Jurnal Gaussian, vol. 9, no. 3, pp. 306–315, Aug. 2020, doi: 10.14710/j.gauss.v9i3.28912.
[20] I. W. McBrearty and G. C. Beroza, “Earthquake Phase Association with Graph Neural Networks,” Bulletin of the Seismological Society of America, vol. 113, no. 2, pp. 524–547, Apr. 2023, doi: 10.1785/0120220182.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rendinis Rendinis, Makhsun Makhsun, Choirul Basir, Naufal Naufal
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
