Spatial-Temporal Analysis of Earthquakes in Indonesia  with Deep Learning Models: Performance Evaluation of CNN, LSTM,  and Hybrid CNN-GRU

Susandri Susandri; Fajrizal Fajrizal; Feldiansyah Bakri Nasution

doi:10.29207/resti.v9i5.6538

Authors

Susandri Susandri Universitas Lancang Kuning
Fajrizal Fajrizal Universitas Lancang Kuning
Feldiansyah Bakri Nasution University of Lancang Kuning

DOI:

https://doi.org/10.29207/resti.v9i5.6538

Keywords:

bidirectional LSTM, deep learning, earthquake prediction, Hybrid CNN-GRU, spatiotemporal analysis

Abstract

Indonesia, located along the Pacific Ring of Fire, experiences high seismic activity with over 6,000 earthquakes annually. Accurate earthquake prediction remains a major challenge because of the complexity of geological dynamics and limitations of traditional methods in capturing nonlinear seismic patterns. Although deep learning approaches have shown promise, previous studies have often treated spatial and temporal analyses separately, limiting holistic predictive performance. This study proposes a novel hybrid CNN-GRU deep learning model that integrates spatial feature extraction CNN and temporal sequence modeling GRU, and compares its performance with of that CNN, LSTM, GRU, and Bidirectional LSTM using a dataset of 117,251 earthquake events in Indonesia (2008–2024). The results show that Bidirectional LSTM achieved the best temporal accuracy (R² 0.653, RMSE 0.592), while the hybrid CNN-GRU provided balanced spatial-temporal performance (R² 0.587). Notably, the performance gap between Bidirectional LSTM and other models (e.g., Hybrid CNN-GRU) was statistically validated via paired t-test (p < 0.05). The proposed models generalize well to unseen regions such as Maluku-Papua. The key contribution is the hybridization of spatial-temporal learning in a single-model architecture - where CNN processes latitude-longitude coordinates via 1D convolutions while GRU handles temporal sequences - an approach lacking in earlier works. This directly improves early warning systems in seismically active areas by providing 32% higher accuracy than conventional methods.

Downloads

Download data is not yet available.

References

M. A. Permana and M. Faisal, “Uji Performa Prediksi Gempa Bumi di Jawa Timur dengan Artificial Neural Network,” Euler J. Ilm. Mat. Sains dan Teknol., vol. 11, no. 1, pp. 44–54, 2023, doi: 10.34312/euler.v11i1.19291.

V. M. Velasco Herrera et al., “Long-Term Forecasting of Strong Earthquakes in North America, South America, Japan, Southern China and Northern India With Machine Learning,” Front. Earth Sci., vol. 10, no. June 2022, pp. 1–25, 2022, doi: 10.3389/feart.2022.905792.

B. Sadhukhan, S. Chakraborty, S. Mukherjee, and R. K. Samanta, “Climatic and seismic data-driven deep learning model for earthquake magnitude prediction,” Front. Earth Sci., vol. 11, no. February, pp. 1–24, 2023, doi: 10.3389/feart.2023.1082832.

S. Bhatta and J. Dang, “Seismic damage prediction of RC buildings using machine learning,” Earthq. Eng. Struct. Dyn., vol. 52, no. 11, pp. 3504–3527, 2023, doi: 10.1002/eqe.3907.

V. Convertito, F. Giampaolo, O. Amoroso, and F. Piccialli, “Deep learning forecasting of large induced earthquakes via precursory signals,” Sci. Rep., vol. 14, no. 1, pp. 1–17, 2024, doi: 10.1038/s41598-024-52935-2.

M. A. Rusho, R. Azizova, D. Mykhalevskiy, M. Karyonov, and H. Hasanova, “Advanced Earthquake Prediction: Unifying Networks, Algorithms, and Attention-Driven Lstm Modelling,” Int. J. GEOMATE, vol. 27, no. 119, pp. 135–142, 2024, doi: 10.21660/2024.119.m2415.

Y. Liu, Q. Zhao, and Y. Wang, “Peak ground acceleration prediction for on-site earthquake early warning with deep learning,” Sci. Rep., vol. 14, no. 1, pp. 1–15, 2024, doi: 10.1038/s41598-024-56004-6.

S. N, B. S, J. Jesudas, D. Ponnarian, A. Nair, and H. B, “Analysis of Seismic Activity Using Deep Learning,” 2024 IEEE 16th Int. Conf. Comput. Intell. Commun. Networks, pp. 213–217, 2024, doi: 10.1109/CICN63059.2024.10847444.

J. Chen, A. Che, L. Wang, and H. Zhou, “Dynamic response prediction for slope during earthquake using modal analysis and deep learning methods,” Comput. Geotech., 2024, doi: 10.1016/j.compgeo.2024.106618.

W. Kuang, J. Zhang, and W. Zhang, “A novel deep-learning image condition for locating earthquake,” Geophys. J. Int., vol. 235, no. 3, pp. 2168–2178, 2023, doi: 10.1093/gji/ggad350.

P. Kavianpour, M. Kavianpour, E. Jahani, and A. Ramezani, “A CNN-BiLSTM model with attention mechanism for earthquake prediction,” J. Supercomput., vol. 79, no. 17, pp. 19194–19226, 2023, doi: 10.1007/s11227-023-05369-y.

A. Berhich, F.-Z. Belouadha, and M. I. Kabbaj, “A location-dependent earthquake prediction using recurrent neural network algorithms,” Soil Dyn. Earthq. Eng., vol. 161, p. 107389, 2022, doi: https://doi.org/10.1016/j.soildyn.2022.107389.

R. Jena et al., “An Integration of Deep Learning and Transfer Learning for Earthquake-Risk Assessment in the Eurasian Region,” Remote Sens., vol. 15, no. 15, pp. 1–24, 2023, doi: 10.3390/rs15153759.

C. Zhu, F. Cotton, H. Kawase, and K. Nakano, “How well can we predict earthquake site response so far? Machine learning vs physics-based modeling,” Earthq. Spectra, vol. 39, no. 1, pp. 478–504, 2023, doi: 10.1177/87552930221116399.

O. Somantri, S. Purwaningrum, and R. Riyanto, “Model Support Vektor Machine (Svm) Berdasarkan Parameter Windows Untuk Prediksi Kekuatan Gempa Bumi,” JTT (Jurnal Teknol. Ter., vol. 8, no. 1, p. 17, 2022, doi: 10.31884/jtt.v8i1.352.

J. Jia and W. Ye, “Deep Learning for Earthquake Disaster Assessment: Objects, Data, Models, Stages, Challenges, and Opportunities,” Remote Sens., vol. 15, no. 16, pp. 1–41, 2023, doi: 10.3390/rs15164098.

Z. Aizzah, P. K. Intan, and W. D. Utami, “Prediksi Jumlah Gempa Tektonik di Wilayah Jawa Timur dengan Menggunakan Metode ARIMA Box Jenkins dan Kalman Filter,” JRST (Jurnal Ris. Sains dan Teknol., vol. 5, no. 2, p. 111, 2022, doi: 10.30595/jrst.v5i2.9701.

S. M. Mousavi and G. C. Beroza, “Machine Learning in Earthquake Seismology,” Annu. Rev. Earth Planet. Sci., vol. 51, pp. 105–129, 2023, doi: 10.1146/annurev-earth-071822-100323.

J. Song, J. Zhu, Y. Wang, and S. Li, “On-site alert-level earthquake early warning using machine-learning-based prediction equations,” Geophys. J. Int., vol. 231, no. 2, pp. 786–800, 2022, doi: 10.1093/gji/ggac220.

J. Ir, S. No, and J. Tengah, “Prediksi Gempa Bumi di Yogyakarta Berdasarkan Nilai Magnitudo , Kedalaman , dan Lokasi Gempa Menggunakan Naïve Bayes,” PETIR J. Pengkaj. dan Penerapan Tek. Inform., vol. 17, no. 1, pp. 122–132, 2024.

D. Muhammad, I. Ahmad, M. I. Khalil, W. Khalil, and M. O. Ahmad, “A Generalized Deep Learning Approach to Seismic Activity Prediction,” Appl. Sci., vol. 13, no. 3, pp. 1–13, 2023, doi: 10.3390/app13031598.

A. Fauzan and D. Ahmad, “Analisis Hasil Prediksi Magnitudo Gempa Di Wilayah Kota Padang Menggunakan Teknik Random Forest,” J. Lebesgue J. Ilm. Pendidik. Mat. Mat. dan Stat., vol. 4, no. 3, pp. 1569–1576, 2023, doi: 10.46306/lb.v4i3.450.

S. Susandri, A. Zamsuri, N. Nasution, Y. Efendi, and H. B. Alwan, “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.v24i1.4742.

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.

S. K C, A. Bhusal, D. Gautam, and R. Rupakhety, “Earthquake damage and rehabilitation intervention prediction using machine learning,” Eng. Fail. Anal., vol. 144, p. 106949, 2023, doi: https://doi.org/10.1016/j.engfailanal.2022.106949.

A. Pyakurel, B. K. Dahal, and D. Gautam, “Does machine learning adequately predict earthquake induced landslides?,” Soil Dyn. Earthq. Eng., vol. 171, p. 107994, 2023, doi: https://doi.org/10.1016/j.soildyn.2023.107994.

C. Cosgun, “Machine learning for the prediction of evaluation of existing reinforced concrete structures performance against earthquakes,” Structures, vol. 50, pp. 1994–2003, 2023, doi: https://doi.org/10.1016/j.istruc.2023.02.127.

N. S. M. Ridzwan and S. H. M. Yusoff, “Machine learning for earthquake prediction: a review (2017–2021),” Earth Sci. Informatics, vol. 16, no. 2, pp. 1133–1149, 2023, doi: 10.1007/s12145-023-00991-z.

P. Chittora et al., “Experimental analysis of earthquake prediction using machine learning classiers, curve tting, and neural modeling,” PREPRINT, vol. 2, pp. 1–26, 2022, [Online]. Available: https://doi.org/10.21203/rs.3.rs-1896823/v2

A. Berhich, F.-Z. Belouadha, and M. I. Kabbaj, “An attention-based LSTM network for large earthquake prediction,” Soil Dyn. Earthq. Eng., vol. 165, p. 107663, 2023, doi: https://doi.org/10.1016/j.soildyn.2022.107663.

M. S. Abdalzaher, H. A. Elsayed, M. M. Fouda, and M. M. Salim, “Employing Machine Learning and IoT for Earthquake Early Warning System in Smart Cities,” Energies, vol. 16, no. 1, pp. 1–22, 2023, doi: 10.3390/en16010495.

M. S. Bandstra, J. C. Curtis, J. M. Ghawaly, A. C. Jones, and T. H. Y. Joshi, “Explaining machine-learning models for gamma-ray detection and identification,” PLoS One, vol. 18, no. 6 JUNE, pp. 1–21, 2023, doi: 10.1371/journal.pone.0286829.

E. Amico, L. Matteucci, and G. Cafiero, “Data-driven insights into jet turbulence: Explainable AI approaches,” Phys. Fluids, vol. 37, no. 5, p. 55108, May 2025, doi: 10.1063/5.0268702.