講演情報
[U18-04]データ同化を用いた断層すべりの現状把握および短期推移予測★招待講演
*加納 将行1,2 (1.京都大学防災研究所、2.海洋研究開発機構)
キーワード：
データ同化、物理深層学習、断層すべり、GNSS
Monitoring and forecasting fault slip behavior in subduction zones is essential for understanding earthquake cycles and assessing future earthquake potential. In this presentation, I will introduce a series of studies that apply data assimilation to fault slip monitoring and short-term forecasting of the 2010 Bungo Channel slow slip event. In particular, I will demonstrate the potential of physics-informed neural networks potential to advance our understanding of fault mechanics and to enable physics-based fault slip forecasting.
References:
-Fukushima et al. (2023). Physics-informed neural networks for fault slip monitoring: Simulation, frictional parameter estimation, and prediction on slow slip events in a spring-slider system. Journal of Geophysical Research: Solid Earth, 128, e2023JB027384. https://doi.org/10.1029/2023JB027384
-Kano et al. (2024). Data assimilation for fault slip monitoring and short-term prediction of spatio-temporal evolution of slow slip events: application to the 2010 long-term slow slip event in the Bungo Channel, Japan. Earth Planets Space 76, 57. https://doi.org/10.1186/s40623-024-02004-9
-Fukushima et al. (2025). Physics-informed deep learning for estimating the spatial distribution of frictional parameters in slow slip regions. Journal of Geophysical Research: Solid Earth, 130, e2024JB030256. https://doi.org/10.1029/2024JB030256
-Fukushima et al. (2026). Physics-informed deep learning links geodetic data and fault friction. arXiv: https://doi.org/10.48550/arXiv.2601.20136
-Kano and Fukushima (2026). PINN-based short-term forecasting of fault slip evolution during the 2010 slow slip event in the Bungo Channel, Japan. arXiv: https://doi.org/10.48550/arXiv.2601.21516
References:
-Fukushima et al. (2023). Physics-informed neural networks for fault slip monitoring: Simulation, frictional parameter estimation, and prediction on slow slip events in a spring-slider system. Journal of Geophysical Research: Solid Earth, 128, e2023JB027384. https://doi.org/10.1029/2023JB027384
-Kano et al. (2024). Data assimilation for fault slip monitoring and short-term prediction of spatio-temporal evolution of slow slip events: application to the 2010 long-term slow slip event in the Bungo Channel, Japan. Earth Planets Space 76, 57. https://doi.org/10.1186/s40623-024-02004-9
-Fukushima et al. (2025). Physics-informed deep learning for estimating the spatial distribution of frictional parameters in slow slip regions. Journal of Geophysical Research: Solid Earth, 130, e2024JB030256. https://doi.org/10.1029/2024JB030256
-Fukushima et al. (2026). Physics-informed deep learning links geodetic data and fault friction. arXiv: https://doi.org/10.48550/arXiv.2601.20136
-Kano and Fukushima (2026). PINN-based short-term forecasting of fault slip evolution during the 2010 slow slip event in the Bungo Channel, Japan. arXiv: https://doi.org/10.48550/arXiv.2601.21516