Physics-informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determination
Abstract Subsurface seismic velocity structure is essential for earthquake source studies, including hypocenter determination. Conventional hypocenter determination methods ignore the inherent uncertainty in seismic velocity structure models, and the impact of this oversight has not been thoroughly...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-84995-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594738310545408 |
|---|---|
| author | Ryoichiro Agata Kazuya Shiraishi Gou Fujie |
| author_facet | Ryoichiro Agata Kazuya Shiraishi Gou Fujie |
| author_sort | Ryoichiro Agata |
| collection | DOAJ |
| description | Abstract Subsurface seismic velocity structure is essential for earthquake source studies, including hypocenter determination. Conventional hypocenter determination methods ignore the inherent uncertainty in seismic velocity structure models, and the impact of this oversight has not been thoroughly investigated. Here, we address this issue by employing a physics-informed deep learning (PIDL) approach that quantifies uncertainty in two-dimensional seismic velocity structure modeling and its propagation to hypocenter determination by introducing neural network ensembles trained on active seismic survey data, earthquake observation data, and the physical equation of wavefront movement. An analysis of an earthquake in southwest Japan using our method revealed that accounting for such uncertainty propagation significantly reduced the bias and uncertainty underestimation in the hypocenter determination, enabling quantitative evaluation of the focal depth relative to the plate boundary. Our results highlight the potential of PIDL for various geophysical inverse problems, such as investigating earthquake source parameters, which inherently suffer from uncertainty propagation. |
| format | Article |
| id | doaj-art-075e9693033c410ab959a02a6352cdce |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-075e9693033c410ab959a02a6352cdce2025-01-19T12:21:55ZengNature PortfolioScientific Reports2045-23222025-01-0115111410.1038/s41598-024-84995-9Physics-informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determinationRyoichiro Agata0Kazuya Shiraishi1Gou Fujie2Japan Agency for Marine-Earth Science and TechnologyJapan Agency for Marine-Earth Science and TechnologyJapan Agency for Marine-Earth Science and TechnologyAbstract Subsurface seismic velocity structure is essential for earthquake source studies, including hypocenter determination. Conventional hypocenter determination methods ignore the inherent uncertainty in seismic velocity structure models, and the impact of this oversight has not been thoroughly investigated. Here, we address this issue by employing a physics-informed deep learning (PIDL) approach that quantifies uncertainty in two-dimensional seismic velocity structure modeling and its propagation to hypocenter determination by introducing neural network ensembles trained on active seismic survey data, earthquake observation data, and the physical equation of wavefront movement. An analysis of an earthquake in southwest Japan using our method revealed that accounting for such uncertainty propagation significantly reduced the bias and uncertainty underestimation in the hypocenter determination, enabling quantitative evaluation of the focal depth relative to the plate boundary. Our results highlight the potential of PIDL for various geophysical inverse problems, such as investigating earthquake source parameters, which inherently suffer from uncertainty propagation.https://doi.org/10.1038/s41598-024-84995-9 |
| spellingShingle | Ryoichiro Agata Kazuya Shiraishi Gou Fujie Physics-informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determination Scientific Reports |
| title | Physics-informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determination |
| title_full | Physics-informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determination |
| title_fullStr | Physics-informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determination |
| title_full_unstemmed | Physics-informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determination |
| title_short | Physics-informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determination |
| title_sort | physics informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determination |
| url | https://doi.org/10.1038/s41598-024-84995-9 |
| work_keys_str_mv | AT ryoichiroagata physicsinformeddeeplearningquantifiespropagateduncertaintyinseismicstructureandhypocenterdetermination AT kazuyashiraishi physicsinformeddeeplearningquantifiespropagateduncertaintyinseismicstructureandhypocenterdetermination AT goufujie physicsinformeddeeplearningquantifiespropagateduncertaintyinseismicstructureandhypocenterdetermination |