Systematic Literature Review Penerapan Physics-Informed Machine Learning untuk Analisis Seismisitas dan Bahaya Gempa Bumi

Abdul Hakim Prima Yuniarto; Fandy Setyo Utomo; Giat Karyono

doi:10.30865/json.v7i4.9830

Authors

Abdul Hakim Prima Yuniarto Universitas Amikom Purwokerto
Fandy Setyo Utomo Universitas Amikom Purwokerto
Giat Karyono Universitas Amikom Purwokerto

DOI:

https://doi.org/10.30865/json.v7i4.9830

Keywords:

Gempa Bumi, Physics-Informed Machine Learning, Physics-Informed Neural Networks, Seismologi, Tinjauan Literatur Sistematis

Abstract

Pendekatan machine learning konvensional yang murni berbasis data dalam bidang seismologi sering kali menghasilkan model kotak hitam yang melanggar hukum fisika dasar serta memerlukan data pelabelan masif. Sebagai solusi, paradigma Physics-Informed Machine Learning (PIML) hadir mengintegrasikan pengetahuan domain fisis ke dalam arsitektur kecerdasan buatan. Penelitian ini bertujuan melakukan tinjauan literatur sistematis (Systematic Literature Review/SLR) untuk memetakan mekanisme integrasi, klaster parameter, dampak komputasi, serta kesenjangan riset dari penerapan PIML pada analisis kegempaan. Melalui evaluasi terstruktur terhadap 36 studi utama rentang 2021–2026, hasil analisis menunjukkan bahwa integrasi hukum fisika dominan dilakukan melalui modifikasi fungsi kerugian memanfaatkan residu persamaan diferensial parsial. Penerapan paradigma ini pada sejumlah studi terbukti mampu meningkatkan efisiensi komputasi serta mempercepat waktu simulasi numerik dibandingkan dengan metode konvensional, serta menyajikan pemodelan tanpa jaring yang stabil pada frekuensi tinggi. Namun, analisis kesenjangan mengungkap adanya ketergantungan pada skema terpandu deterministik. Riset ini merekomendasikan arah pengembangan masa depan pada integrasi metode unsupervised dan konstrain statistik seismologi guna menjamin kemasukakalan fisis model.

References

[1] A. S. Nyamawe, M. M. Mjahidi, N. E. Nnko, S. A. Diwani, G. G. Minja, and K. Malyango, Practical Machine Learning. Oxon: CRC Press, 2025. doi: https://doi.org/10.1201/9781003486817.

[2] V. Acquaviva, Machine Learning for Physics and Astronomy. New Jersey: Princeton University Press, 2023.

[3] G. E. Karniadakis, I. G. Kevrekidis, L. Lu, P. Perdikaris, S. Wang, and L. Yang, “Physics-informed machine learning,” Nat. Rev. Phys., no. May, 2021, doi: https://doi.org/10.1038/s42254-021-00314-5.

[4] Z. Ren, S. Zhou, D. Liu, and Q. Liu, “Physics-Informed Neural Networks A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific Computing,” Appl. Sci., vol. 5, no. 8092, 2025, doi: Applhttps://doi.org/10.3390/app15148092.

[5] M. Habib, A. Habib, and B. Alibrahim, “Applications of physics-informed neural networks in geosciences : From basic seismology to comprehensive environmental studies,” Open Geosci., vol. 17, pp. 1–21, 2025, doi: https://doi.org/10.1515/geo-2025-0853.

[6] M. Reichstein, G. Camps-valls, B. Stevens, M. Jung, J. Denzler, and N. Carvalhais, “Deep learning and process understanding for data-driven Earth system science,” Nature, vol. 566, 2019, doi: https://doi.org/10.1038/s41586-019-0912-1.

[7] S. Karimpouli and P. Tahmasebi, “Physics informed machine learning : Seismic wave equation,” Geosci. Front., vol. 11, no. 6, pp. 1993–2001, 2020, doi: https://doi.org/10.1016/j.gsf.2020.07.007.

[8] D. Ji, Y. Chen, C. Zhai, C. Zhu, and L. Xie, “One-dimensional shear-wave velocity profile inversion using deep learning guided by wave physics,” Soil Dyn. Earthq. Eng., vol. 190, p. 109186, 2025, doi: https://doi.org/10.1016/j.soildyn.2024.109186.

[9] S. Yang, R. Chen, and P. Deng, “Feature encoded physical-informed neural network modelling incorporated neural tangent kernel analysis for wave propagation,” Eng. Appl. Artif. Intell., vol. 163, no. P5, p. 113122, 2026, doi: https://doi.org/10.1016/j.engappai.2025.113122.

[10] M. J. Page et al., “The PRISMA 2020 statement : an updated guideline for reporting systematic reviews,” BMJ, 2021, doi: https://doi.org/10.1136/bmj.n71.

[11] M. M. Abedi, D. Pardo, and T. Alkhalifah, “Gabor-enhanced physics-informed neural networks for fast simulations of acoustic wavefields,” Neural Networks, vol. 193, p. 107978, 2026, doi: https://doi.org/10.1016/j.neunet.2025.107978.

[12] M. M. Abedi, D. Pardo, and T. Alkhalifah, “Least-squares-embedded optimization for accelerated convergence of PINNs in high-frequency acoustic wavefield simulations,” Comput. Geosci., vol. 212, p. 106162, 2026, doi: https://doi.org/10.1016/j.cageo.2026.106162.

[13] Z. Cheng, X. Wang, G. Mao, W. Mao, and S. Cheng, “Meta-transfer learning for efficient initialization of neural network wavefield solutions,” J. Appl. Geophys., vol. 246, p. 106116, 2026, doi: https://doi.org/10.1016/j.jappgeo.2026.106116.

[14] Y. Ding, S. Chen, X. Li, L. Jin, S. Luan, and H. Sun, “Physics-constrained neural networks for half-space seismic wave modeling,” Comput. Geosci., vol. 181, no. May, p. 105477, 2023, doi: https://doi.org/10.1016/j.cageo.2023.105477.

[15] J. Fayaz, R. Astroza, and S. Ruiz, “An Interpretable and Domain-Informed Real-Time Hybrid Earthquake Early Warning for Ground Shaking Intensity Prediction,” Engineering, vol. 49, pp. 190–204, 2025, doi: https://doi.org/10.1016/j.eng.2025.03.009.

[16] H. Taghavi Ganji and E. Seylabi, “Physics-informed neural network modeling of one-dimensional wave propagation under broadband and long-duration incident waves,” Comput. Geotech., vol. 189, p. 107652, 2026, doi: https://doi.org/10.1016/j.compgeo.2025.107652.

[17] B. Gao, J. Wang, Y. Wang, B. Du, Z. Tian, and W. Shi, “Physics-informed synergy regional co-seismic landslide size prediction: A novel data-driven approach for improved reliability and interpretability,” Geosci. Front., vol. 17, no. 4, p. 102297, 2026, doi: https://doi.org/10.1016/j.gsf.2026.102297.

[18] H. Geng, C. Song, U. bin Waheed, and C. Liu, “Seismic first-arrival traveltime simulation based on reciprocity-constrained PINN,” J. Appl. Geophys., vol. 243, p. 105967, 2025, doi: https://doi.org/10.1016/j.jappgeo.2025.105967.

[19] S. Grubas, A. Duchkov, and G. Loginov, “Neural Eikonal solver: Improving accuracy of physics-informed neural networks for solving eikonal equation in case of caustics,” J. Comput. Phys., vol. 474, p. 111789, 2023, doi: https://doi.org/10.1016/j.jcp.2022.111789.

[20] K. Ji, P. Wen, X. Cao, Y. Ren, and Q. Qi, “Conditional simulation of spatially correlated nonstationary ground motions using a physics-informed machine learning approach,” Mech. Syst. Signal Process., vol. 241, 2025, doi: https://doi.org/10.1016/j.ymssp.2025.113494.

[21] J. P. Vantassel and S. Bhochhibhoya, “Toward more-robust , AI-enabled subsurface seismic imaging for geotechnical applications,” Comput. Geotech., vol. 187, no. July, p. 107443, 2025, doi: https://doi.org/10.1016/j.compgeo.2025.107443.

[22] J.-H. Kim, Y. H. Lee, J.-W. Baek, and D.-J. Kim, “A data-driven approach for spectrum-matched earthquake ground moKim, J.-H., Lee, Y. H., Baek, J.-W., & Kim, D.-J. (2025). A data-driven approach for spectrum-matched earthquake ground motions with physics-informed neural networks. Developments in the Buil,” Dev. Built Environ., vol. 21, p. 100598, 2025, doi: https://doi.org/10.1016/j.dibe.2024.100598.

[23] Z. Li, D. Wang, S. Yan, H. Chen, Z. Zhang, and W. Li, “Characterizing irregularly shaped rockfall dynamics using seismic signals : Geometric source effects combined with deep learning-driven strategy,” J. Rock Mech. Geotech. Eng., no. xxxx, 2026, doi: https://doi.org/10.1016/j.jrmge.2026.03.005.

[24] Y. Li, J.-M. Zhang, and R. Wang, “A PINN-driven stress integration paradigm for high-fidelity soil constitutive model considering cyclic response,” Comput. Geotech., vol. 196, p. 108170, 2026, doi: https://doi.org/10.1016/j.compgeo.2026.108170.

[25] C. Liu, J. Macedo, and A. Rodríguez, “Leveraging physics-informed neural networks in geotechnical earthquake engineering: An assessment on seismic site response analyses,” Comput. Geotech., vol. 182, 2025, doi: 10.1016/j.compgeo.2025.107137.

[26] Z. Liu, G. Archibong, U. bin Waheed, S. Wang, and C. Song, “Physics-Informed Fourier-DeepONet for a generalized eikonal solution,” Comput. Geosci., vol. 206, no. February 2025, p. 106026, 2026, doi: https://doi.org/10.1016/j.cageo.2025.106026.