Conference proceeding
An Efficient Bayesian Traveltime Tomography Method with Uncertainty Quantification
IEEE International Geoscience and Remote Sensing Symposium proceedings, pp.3902-3905
08/03/2025
DOI: 10.1109/IGARSS55030.2025.11243627
Abstract
In recent years, uncertainty quantification has received growing attention in geophysics. However, conventional Bayesian traveltime tomography methods are often computationally expensive. This paper presents an efficient seismic traveltime tomography method, which combines Bayesian Physics-Informed Neural Networks with Dropout Ensemble Kalman Inversion (DEKI-BPINNs) to infer velocity fields and supply uncertainty quantification in inverse results. In standard Ensemble Kalman Inversion (EKI), each ensemble member requires one forward simulation through the neural network per iteration. In contrast, DEKI needs a smaller ensemble size, which reduces the total number of forward simulations per iteration, making it more computationally efficient. Numerical results demonstrate that DEKI-BPINNs are computationally efficient while inferring relatively accurate velocity fields and providing reliable uncertainty quantification.
Details
- Title: Subtitle
- An Efficient Bayesian Traveltime Tomography Method with Uncertainty Quantification
- Creators
- Yunduo Li - Xi'an Jiaotong UniversityYijie Zhang - Xi'an Jiaotong UniversityXueyu Zhu - The University of Iowa,Iowa City,USA,52246Haixia Zhao - Xi'an Jiaotong UniversityJinghuai Gao - Xi'an Jiaotong University
- Resource Type
- Conference proceeding
- Publication Details
- IEEE International Geoscience and Remote Sensing Symposium proceedings, pp.3902-3905
- DOI
- 10.1109/IGARSS55030.2025.11243627
- eISSN
- 2153-7003
- Publisher
- IEEE
- Language
- English
- Date published
- 08/03/2025
- Academic Unit
- Mathematics
- Record Identifier
- 9985090623002771
Metrics
1 Record Views