Journal article
Efficient Bayesian Physics Informed Neural Networks for Surface Tomography via Ensemble Kalman Inversion
Geophysics, Vol.90(3), pp.U1-U14
05/01/2025
DOI: 10.1190/geo2023-0493.1
Abstract
Surface travel-time tomography is a widely-used method to characterize the structure of the underground. However, conventional seismic tomography techniques often require a high-fidelity numerical forward model, which leads to significant computational burden and time consumption. Additionally, the inverse problem in travel-time tomography is prone to ill-posedness and lacks uncertainty quantification for the inferred results.
Details
- Title: Subtitle
- Efficient Bayesian Physics Informed Neural Networks for Surface Tomography via Ensemble Kalman Inversion
- Creators
- Yunduo Li - Xi'an Jiaotong UniversityAndrew Pensoneault - University of IowaYijie Zhang - Xi'an Jiaotong UniversityXueyu Zhu - University of IowaRongxi Gou - Xi'an Jiaotong UniversityJinghuai Gao - Xi'an Jiaotong University
- Resource Type
- Journal article
- Publication Details
- Geophysics, Vol.90(3), pp.U1-U14
- DOI
- 10.1190/geo2023-0493.1
- ISSN
- 0016-8033
- eISSN
- 1942-2156
- Language
- English
- Electronic publication date
- 01/06/2025
- Date published
- 05/01/2025
- Academic Unit
- Mathematics
- Record Identifier
- 9984771625602771
Metrics
12 Record Views