To meet the growing need for accurate and timely tsunami height predictions, a database comprising 3480 high-precision tsunami simulation scenarios for the Nankai Trough was constructed in this study. The database includes the Dense Oceanfloor Network for Earthquakes and Tsunamis (DONET) seafloor pressure sensor data and the maximum tsunami heights for 19 coastal cities. Gaussian process regression with automatic relevance determination (ARD) was used to quantitatively evaluate the effectiveness of each sensor location. In this framework, the ARD assigns a hyperparameter that functions as an indicator of the contribution of each sensor to the prediction. The proportion of this hyperparameter reflects the effectiveness of each sensor during the prediction process. The results demonstrated that removing the 20 least effective sensors (as identified by the ARD) led to an 11% increase in the estimation error, whereas removing the 10 most effective sensors resulted in a 38% increase. These results demonstrate that the proposed method enables the optimization of the sensor placement process and allows for a prior evaluation of the trade-off between the number of sensors and achieved prediction accuracy. This method offers a robust framework for optimizing observation networks, enhancing the accuracy of tsunami predictions, and supporting future disaster risk reduction.

1. [1] O. Kamigaichi et al., “Earthquake early warning in Japan: Warning the general public and future prospects,” Seismological Research Letters, Vol.80, No.5, pp. 717-726, 2009. https://doi.org/10.1785/gssrl.80.5.717
2. [2] S. Ozawa et al., “Coseismic and postseismic slip of the 2011 magnitude-9 Tohoku-Oki earthquake,” Nature, Vol.475, No.7356, pp. 373-376, 2011. https://doi.org/10.1038/nature10227
3. [3] M. Simons et al., “The 2011 magnitude 9.0 Tohoku-Oki earthquake: Mosaicking the megathrust from seconds to centuries,” Science, Vol.332, No.6036, pp. 1421-1425, 2011. https://doi.org/10.1126/science.1206731
4. [4] K. Satake, Y. Fujii, T. Harada, and Y. Namegaya, “Time and space distribution of coseismic slip of the 2011 Tohoku earthquake as inferred from tsunami waveform data,” Bulletin of the Seismological Society of America, Vol.103, No.2B, pp. 1473-1492, 2013. https://doi.org/10.1785/0120120122
5. [5] M. Hoshiba and K. Iwakiri, “Initial 30 seconds of the 2011 off the Pacific coast of Tohoku earthquake (M_w 9.0)—amplitude and τ_c for magnitude estimation for Earthquake Early Warning—,” Earth, Planets and Space, Vol.63, No.7, Article No.8, 2011. https://doi.org/10.5047/eps.2011.06.015
6. [6] N. Mori, T. Takahashi, and the 2011 Tohoku Earthquake Tsunami Joint Survey Group, “Nationwide post event survey and analysis of the 2011 Tohoku earthquake tsunami,” Coastal Engineering J., Vol.54, No.1, Article No.1250001, 2012. https://doi.org/10.1142/S0578563412500015
7. [7] Y. Kaneda et al., “Development and application of an advanced ocean floor network system for megathrust earthquakes and tsunamis,” P. Favali, L. Beranzoli, and A. De Santis (Eds.), “Seafloor Observatories: A New Vision of the Earth from the Abyss,” pp. 643-662, Springer, 2015. https://doi.org/10.1007/978-3-642-11374-1_25
8. [8] Y. Kaneda et al., “Advanced real time monitoring system and simulation researches for earthquakes and tsunamis in Japan,” V. Santiago-Fandiño, Y. A. Kontar, Y. Kaneda (Eds.), “Post-Tsunami Hazard: Reconstruction and Restoration,” pp. 179-189, Springer, 2015. https://doi.org/10.1007/978-3-319-10202-3_12
9. [9] M. Mochizuki et al., “S-net project: Performance of a large-scale seafloor observation network for preventing and reducing seismic and tsunami disasters,” 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans, 2018. https://doi.org/10.1109/OCEANSKOBE.2018.8558823
10. [10] E. Bernard and V. Titov, “Evolution of tsunami warning systems and products,” Philosophical Trans. of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol.373, No.2053, Article No.20140371, 2015. https://doi.org/10.1098/rsta.2014.0371
11. [11] Y. Wang, K. Satake, T. Maeda, and A. R. Gusman, “Green’s function-based tsunami data assimilation: A fast data assimilation approach toward tsunami early warning,” Geophysical Research Letters, Vol.44, No.20, pp. 10282-10289, 2017. https://doi.org/10.1002/2017GL075307
12. [12] J. Selva et al., “Probabilistic tsunami forecasting for early warning,” Nature Communications, Vol.12, Article No.5677, 2021. https://doi.org/10.1038/s41467-021-25815-w
13. [13] Z. Ren et al., “Optimal deployment of seafloor observation network for tsunami data assimilation in the South China Sea,” Ocean Engineering, Vol.243, Article No.110309, 2022. https://doi.org/10.1016/j.oceaneng.2021.110309
14. [14] A. Musa et al., “A real-time tsunami inundation forecast system using vector supercomputer SX-ACE,” J. Disaster Res., Vol.13, No.2, pp. 234-244, 2018. https://doi.org/10.20965/jdr.2018.p0234
15. [15] T. Baba, N. Takahashi, and Y. Kaneda, “Near-field tsunami amplification factors in the Kii Peninsula, Japan for Dense Oceanfloor Network for Earthquakes and Tsunamis (DONET),” Marine Geophysical Research, Vol.35, No.3, pp. 319-325, 2014. https://doi.org/10.1007/s11001-013-9189-1
16. [16] Y. Igarashi et al., “Maximum tsunami height prediction using pressure gauge data by a Gaussian process at Owase in the Kii Peninsula, Japan,” Marine Geophysical Research, Vol.37, No.4, pp. 361-370, 2016. https://doi.org/10.1007/s11001-016-9286-z
17. [17] M. Yoshikawa et al., “A nonlinear parametric model based on a power law relationship for predicting the coastal tsunami height,” Marine Geophysical Research, Vol.40, No.4, pp. 467-477, 2019. https://doi.org/10.1007/s11001-019-09388-4
18. [18] Y. Iwabuchi et al., “Tsunami height estimation via Gaussian process regression using the maximum absolute pressure change and time from seafloor sensors off the Kii Peninsula, Japan,” Marine Geophysical Research, Vol.46, No.3, pp. 22-46, 2025. https://doi.org/10.1007/s11001-025-09583-6
19. [19] J. Taniguchi et al., “Selection of tsunami observation points suitable for database-driven prediction,” J. Disaster Res., Vol.13, No.2, pp. 245-253, 2018. https://doi.org/10.20965/jdr.2018.p0245
20. [20] Y. Igarashi et al., “Three levels of data-driven science,” J. of Physics: Conf. Series, Vol.699, Article No.012001, 2016. https://doi.org/10.1088/1742-6596/699/1/012001
21. [21] Y. Igarashi et al., “Exhaustive search for sparse variable selection in linear regression,” J. of the Physical Society of Japan, Vol.87, No.4, Article No.044802, 2018. https://doi.org/10.7566/JPSJ.87.044802
22. [22] H. Fujiwara et al., “Probabilistic tsunami hazard assessment for earthquakes occurring along the Nankai Trough – Volume 1 Part I –,” Technical Note of the National Research Institute for Earth Science and Disaster Resilience, No.439, 2020.
23. [23] Y. Okada, “Surface deformation due to shear and tensile faults in a half-space,” Bulletin of Seismological Society of America, Vol.75, No.4, pp. 1135-1154, 1985. https://doi.org/10.1785/BSSA0750041135
24. [24] T. Baba et al., “Probabilistic tsunami hazard assessment based on the Gutenberg–Richter law in eastern Shikoku, Nankai subduction zone, Japan,” Earth, Planets and Space, Vol.74, No.1, Article No.156, 2022. https://doi.org/10.1186/s40623-022-01715-1
25. [25] T. Baba et al., “Parallel implementation of dispersive tsunami wave modeling with a nesting algorithm for the 2011 Tohoku tsunami,” Pure and Applied Geophysics, Vol.172, No.12, pp. 3455-3472, 2015. https://doi.org/10.1007/s00024-015-1049-2
26. [26] C. E. Rasmussen and C. K. I. Williams, “Gaussian processes for machine learning,” The MIT Press, 2005. https://doi.org/10.7551/mitpress/3206.001.0001
27. [27] I. E. Mulia, N. Ueda, T. Miyoshi, A. R. Gusman, and K. Satake, “Machine learning-based tsunami inundation prediction derived from offshore observations,” Nature Communications, Vol.13, Article No.5489, 2022. https://doi.org/10.1038/s41467-022-33253-5
28. [28] T. Inoue et al., “Development and validation of a tsunami numerical model with the polygonally nested grid system and its MPI-parallelization for real-time tsunami inundation forecast on a regional scale,” J. Disaster Res., Vol.14, No.3, pp. 416-434, 2019. https://doi.org/10.20965/jdr.2019.p0416