Geodetically-Enhanced Hybrid GRU with Adaptive Dropout and Dynamic L2 Regularization for Earthquake Parameter Prediction in Indonesia

Najmuddin Mubarak MR; Susandri Susandri; Ahmad Zamsuri

doi:10.52436/1.jutif.2026.7.2.5478

Authors

Najmuddin Mubarak MR Computer Science, Universitas Lancang Kuning, Indonesia
Susandri Susandri Computer Science, Universitas Lancang Kuning, Indonesia
Ahmad Zamsuri Computer Science, Universitas Lancang Kuning, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.2.5478

Keywords:

Adaptive Dropout, Dynamic L2, Earthquake Prediction, Hybrid GRU, Slip-Rate Feature

Abstract

Earthquake prediction remains challenging due to the nonlinear behavior and uncertainty of seismic activity. This study introduces a geodetically-enhanced hybrid GRU model integrating adaptive dropout and dynamic L2 regularization to improve robustness and accuracy in earthquake magnitude prediction. In addition to seismic sequence data, slip-rate values derived from scalar moment distribution were incorporated as a domain-informed feature to represent tectonic strain accumulation across Indonesia. The dataset consisted of BMKG records from 2010–2025 and was processed through outlier removal, normalization, temporal reshaping, and feature integration. The proposed model was evaluated against multiple deep learning baselines including CNN-1D, LSTM, standard GRU, Transformer-based models, and Neural ODE architectures. Performance assessment used RMSE, MAE, and R² metrics. The resulting hybrid GRU achieved improved predictive accuracy with an RMSE of 0.5176, MAE of 0.3973, and an R² score of 0.5997, outperforming both CNN-1D and standard GRU baselines. The integration of slip-rate features contributed to reduced prediction variance across tectonically active zones. These findings demonstrate that combining geodetic information with adaptive regularization strategies improves generalization and model stability for seismic forecasting. The approach offers potential applicability for rapid early-warning scenarios requiring low latency and reliable prediction accuracy.

Downloads

Download data is not yet available.

References

Y. Liu, C. Liu, C. Xie, and Q. X. Zhao, “A Hybrid Regularization Operator and Its Application in Seismic Inversion,” IEEE Access, vol. 9, pp. 117378–117387, 2021, doi: 10.1109/ACCESS.2021.3106912.

H. M. Hassan and M. Okubo, “Engineering , Environment , and Technology Seismic Hazard for Regional-Scale Sumatra Island Based on Realistic Physical Computation of Seismic Wave Propagation,” vol. 10, no. 2, pp. 224–231, 2025, doi: 10.25299/jgeet.2025.10.02.21751.

S. Muhammad, A. Putri, F. Cahyani, O. Anggara, M. Dayanti, and A. Rizqiansyah, “Slip Rate of Kumering Fault in Lampung Province Calculated from GPS Data from 2007 to 2021,” vol. 5, no. September, 2022.

A. S. Putra, A. D. Nugraha, D. P. Sahara, N. T. Puspito, F. Muttaqy, and P. Supendi, “Indonesian journal on geoscience,” vol. 10, no. 1, pp. 83–96, 2023, doi: 10.17014/ijog.10.1.83-96.

W. Triyoso et al., “Indonesian journal on geoscience,” vol. 8, no. 1, pp. 1–9, 2021, doi: 10.17014/ijog.8.1.1-9.

P. Ayuningtyas, S. Khomsah, and S. Sudianto, “Pelabelan Sentimen Berbasis Semi-Supervised Learning menggunakan Algoritma LSTM dan GRU,” JISKA (Jurnal Inform. Sunan Kalijaga), vol. 9, no. 3, pp. 217–229, 2024, doi: 10.14421/jiska.2024.9.3.217-229.

O. Somantri, J. Teknik Informatika, and P. Negeri Cilacap, “Seminar Nasional Informatika Bela Negara (SANTIKA) Prediksi Kekuatan Gempa Bumi Indonesia Berdasarkan Nilai Magnitudo Menggunakan Neural Network,” 2021, pp. 203–207.

H. Tantyoko, D. K. Sari, and A. R. Wijaya, “Prediksi Potensial Gempa Bumi Indonesia Menggunakan Metode Random Forest Dan Feature Selection,” IDEALIS Indones. J. Inf. Syst., vol. 6, no. 2, pp. 83–89, 2023, doi: 10.36080/idealis.v6i2.3036.

A. Hakim, P. Yuniarto, T. Hariguna, and D. A. Nawangnugraeni, “Comparison of Accuracy and Computation Time for Predicting Earthquake Magnitude in Java Island,” vol. 6, no. 4, pp. 2811–2824, 2025.

R. E. Saputro and G. Karyono, “Comparative Analysis of Decision Tree , Random Forest , Svm , and Neural Network Models for Predicting Earthquake Magnitude,” vol. 6, no. 2, pp. 755–774, 2025.

P. Y. Maulida, A. Mujib, A. Muhajirin, and A. S. Perdana, “Integration of Deep Learning and Autoregressive Models for Marine Data Prediction,” vol. 24, no. 1, pp. 179–194, 2024, doi: 10.30812/matrik.v24i1.4032.

A. Wijayanto, A. Sugiharto, R. Santoso, U. Diponegoro, and P. Korespondensi, “Identifikasi Dini Curah Hujan Berpotensi Banjir Menggunakan Algoritma Long Short-Term Memory ( Lstm ) Dan Isolation Forest Early Identification Of Rainfall With Flood Potential Using Long Short-Term Memory ( Lstm ) And Isolation Forest Algorithms Case Study Of Semarang Area,” vol. 11, no. 3, 2024, doi: 10.25126/jtiik.938718.

N. Selle, N. Yudistira, C. Dewi, and U. Brawijaya, “Perbandingan Prediksi Penggunaan Listrik Dengan Menggunakan Metode Long Short Term Memory ( Lstm ) Dan Recurrent Neural Network ( Rnn ) Comparison Of Predicting Electricity Consumption Using Long Short Term Memory ( Lstm ) And Recurrent Neural Network ( Rnn ),” vol. 9, no. 1, pp. 155–162, 2022, doi: 10.25126/jtiik.202295585.

B. R. Ermawan and N. Cahyono, “Optimasi Metode Klasifikasi Menggunakan Fasttext Dan Grid Search Pada Analisis Sentimen Ulasan Aplikasi Seabank,” JIKO (Jurnal Inform. dan Komputer), vol. 9, no. 1, p. 226, 2025, doi: 10.26798/jiko.v9i1.1523.

N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” J. Mach. Learn. Res., vol. 15, pp. 1929–1958, 2014, doi : 10.5555/2627435.2670313.

S. Susandri, A. Zamsuri, N. Nasution, Y. Efendi, and H. B. Alwan, “The Mitigating Overfitting in Sentiment Analysis Insights from CNN-LSTM Hybrid Models,” MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 24, no. 2, pp. 297–308, 2025, doi: 10.30812/matrik.v24i2.4742.

E. Y. Fitria, K. Mutijarsa, P. Korespondensi, S. Siber, K. Buatan, and D. Learning, “Research Survey On Artificial Intelligence Methods For Detecting Cyberattack Technology Threats,” vol. 10, no. 6, 2023, doi: 10.25126/jtiik.2023107341.

N. Wayan et al., “Recognizing Pneumonia Infection in Chest X-Ray Using Deep Learning,” vol. 23, no. 1, pp. 17–28, 2023, doi: 10.30812/matrik.v23i1.3197.

M. Tubagus Ahmad Marzuqi, Evelline Kristiani, “Prediksi Mahasiswa Drop-Out Di Universitas Xyz Prediction Of Student Drop-Out At Xyz University,” vol. 11, no. 6, pp. 1345–1350, 2024, doi: 10.25126/jtiik.2024118689.

F. Yasin, M. Raafi, D. Aldo, and M. A. Amrustian, “Multivariate Forecasting of Paddy Production : A Comparative Study of Machine Learning Models,” vol. 6, no. 3, pp. 1431–1442, 2025.

R. D. Respati, S. Soim, and M. Fadhli, “Development of a Distributed Gradient Boosting Forest Algorithm with Residual Connections in Data Classification,” vol. 6, no. 4, pp. 1811–1830, 2025.

Normah, B. Rifai, S. Vambudi, and R. Maulana, “Analisa Sentimen Perkembangan Vtuber Dengan Metode Support Vector Machine Berbasis SMOTE,” J. Tek. Komput. AMIK BSI, vol. 8, no. 2, pp. 174–180, 2022, doi: 10.31294/jtk.v4i2.

A. Rachmadan, A. Koeshidayatullah, and S. L. I. Kaka, “Developing ground motion prediction models for West Java: A machine learning approach to support Indonesia’s earthquake early warning system,” Appl. Comput. Geosci., vol. 25, no. August 2024, p. 100212, 2025, doi: 10.1016/j.acags.2024.100212.

I. O. Arissinta, I. D. Sulistiyawati, D. Kurnianto, and I. Kharisudin, “Pemodelan Time Series untuk Peramalan Web Traffic Menggunakan Algoritma Arima,” in PRISMA, Prosiding Seminar Nasional Matematika, 2022, pp. 693–700. [Online]. Available: https://journal.unnes.ac.id/sju/index.php/prisma/

Roni Merdiansah, Khofifah Wulandari, Mentari Hasibuan, and Yuyun Umaidah, “Perbandingan Kinerja Model RNN, LSTM, dan BLSTM dalam Memprediksi Jumlah Gempa Bulanan di Indonesia,” J. Penelit. Rumpun Ilmu Tek., vol. 3, no. 1, pp. 262–277, 2024, doi: 10.55606/juprit.v3i1.3466.

G. I. Marthasari, S. A. Astiti, and Y. Azhar, “Prediksi Data Time-series menggunakan Jaringan Syaraf Tiruan Algoritma Backpropagation Pada Kasus Prediksi Permintaan Beras,” J. Inform. J. Pengemb. IT, vol. 6, no. 3, pp. 187–193, 2021, doi: 10.30591/jpit.v6i3.2627.

M. Rizki, S. Basuki, and Y. Azhar, “Implementasi Deep Learning Menggunakan Arsitektur Long Short Term Memory(LSTM) Untuk Prediksi Curah Hujan Kota Malang,” J. Repos., vol. 2, no. 3, pp. 331–338, 2020, doi: 10.22219/repositor.v2i3.470.

M. D. Liman, S. O. Ibrahim, E. S. Alu, and S. Zakariya, “Regularization effects in deep learning architecture,” J. Niger. Soc. Phys. Sci., vol. 6, no. 2, p. 1911, 2024, doi: 10.46481/jnsps.2024.1911.

C. Zoremsanga and J. Hussain, “Particle Swarm Optimized Deep Learning Models for Rainfall Prediction: A Case Study in Aizawl, Mizoram,” IEEE Access, vol. 12, no. April, pp. 57172–57184, 2024, doi: 10.1109/ACCESS.2024.3390781.

K. Nakamura, B. S. Sohn, K. J. Won, and B. W. Hong, “Regularization in Network Optimization via Trimmed Stochastic Gradient Descent with Noisy Label,” IEEE Access, vol. 10, pp. 34706–34715, 2022, doi: 10.1109/ACCESS.2022.3171910.

T. G. J. Rudner, S. Kapoor, S. Qiu, and A. G. Wilson, “Function-Space Regularization in Neural Networks: A Probabilistic Perspective,” Proc. Mach. Learn. Res., vol. 202, pp. 29275–29290, 2023.

T. Cinquin, M. Pförtner, V. Fortuin, P. Hennig, and R. Bamler, “FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning,” no. NeurIPS, pp. 1–24, 2024, [Online]. Available: http://arxiv.org/abs/2407.13711

A. Morsali, M. Vaez, H. Soltani, A. Kazerouni, B. Taati, and M. Mohammad-Noori, “STAF: Sinusoidal Trainable Activation Functions for Implicit Neural Representation,” 2025, [Online]. Available: http://arxiv.org/abs/2502.00869

D. A. Hanan, A. Y. Husodo, and R. P. Rassy, “Sentiment Study of ChatGPT on Twitter Data with Hybrid K-Means and LSTM,” vol. 24, no. 2, pp. 273–284, 2025, doi: 10.30812/matrik.v24i2.4791.

E. Harsányi et al., “Assessment of Advanced Machine and Deep Learning Approaches for Predicting CO2 Emissions from Agricultural Lands: Insights Across Diverse Agroclimatic Zones,” Earth Syst. Environ., vol. 8, no. 4, pp. 1109–1125, 2024, doi: 10.1007/s41748-024-00424-x.

Q. Yin, C. Han, A. Li, X. Liu, and Y. Liu, “A Review of Research on Building Energy Consumption Prediction Models Based on Artificial Neural Networks quently , this literature review aims to provide a thorough analysis o types , and temporal characteristics in energy consumption poses guidelines fo,” vol. 16, no. 17, p. 7805, 2024.

B. P. Nandi, G. Singh, A. Jain, and D. K. Tayal, “Evolution of neural network to deep learning in prediction of air, water pollution and its Indian context,” Int. J. Environ. Sci. Technol., vol. 21, no. 1, pp. 1021–1036, 2024, doi: 10.1007/s13762-023-04911-y.

A. A. & A. E.-H. Abdellah Ben Yahia, Iman Kadir, “Enhancing relative humidity modelling using L2 regularization updates.” Pubmed NCBI, p. 14, 2025. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/40295567/

M. I. K. Asmae Berhich, Fatima-Zahra Belouadha, “LSTM-based Models for Earthquake Prediction,” in NISS ’20: Proceedings of the 3rd International Conference on Networking, Information Systems & Security Article, 2020, p. Pages 1-7. [Online]. Available: https://dl.acm.org/doi/10.1145/3386723.3387865?utm_source=chatgpt.com

S. Gonzalez and R. Miikkulainen, “Effective Regularization Through Loss-Function Metalearning,” 2020. [Online]. Available: http://arxiv.org/abs/2010.00788

S. Kiruthiga and S. Mythili, “Prediction of ionospheric TEC during the occurrence of earthquakes in Indonesia using ARMA and CoK models,” Front. Astron. Sp. Sci., vol. 11, no. September, pp. 1–15, 2024, doi: 10.3389/fspas.2024.1415323.

A. Rudyanto et al., “Performance test of pilot Earthquake Early Warning system in western Java, Indonesia,” Int. J. Disaster Risk Reduct., vol. 115, no. February, p. 105010, 2024, doi: 10.1016/j.ijdrr.2024.105010.

D. D. Puspita, S. Steffi, G. Hoendarto, and J. Tjen, “Random Forest Analysis for Predicting the Probability of Earthquake in Indonesia,” Soc. Sci. Humanit. J., vol. 9, no. 01, pp. 6295–6304, 2025, doi: 10.18535/sshj.v9i01.1574.

S. Susandri, S. Defit, and M. Tajuddin, “Enhancing Text Sentiment Classification with Hybrid CNN-BiLSTM Model on WhatsApp Group,” J. Adv. Inf. Technol., vol. 15, no. 3, pp. 355–363, 2024, doi: 10.12720/jait.15.3.355-363.