Uncertainty quantification for travel-time tomography using Deep Operator Networks with randomized priors

Yifan Mei; Yijie Zhang; Xueyu Zhu; Jinghuai Gao

doi:10.1109/TGRS.2024.3524542

Back

Uncertainty quantification for travel-time tomography using Deep Operator Networks with randomized priors

Journal article

Peer reviewed

Uncertainty quantification for travel-time tomography using Deep Operator Networks with randomized priors

Yifan Mei, Yijie Zhang, Xueyu Zhu and Jinghuai Gao

IEEE transactions on geoscience and remote sensing, Vol.63, pp.1-10

2025

DOI: 10.1109/TGRS.2024.3524542

View Online

Abstract

Seismic travel-time tomography is an effective approach for exploring subsurface structures. In recent years, machine learning (ML) has been successfully applied in seismic travel-time tomography; however, the uncertainty quantification of predictive outputs has been less frequently addressed. To tackle these challenges, we adopt the deep ensemble of deep operator networks with randomized priors (DERP-DON) for travel-time tomography, based on measured travel-time data from surface and cross-well measurements. Deep ensembles provide informative uncertainty estimates, and the incorporation of randomized priors allows the network model to offer more conservative uncertainty quantification. Through numerical experiments, we demonstrate that DERP-DON can provide reasonable and conservative uncertainty estimates while accurately inferring the velocity field. Notably, DERP-DON is particularly effective in offering meaningful uncertainty estimates for out-of-distribution data.

Uncertainty

Tomography

Training

Mathematical models

Artificial neural networks

Bayes methods

Computational modeling

Standards

Numerical models

Noise measurement

Deep ensembles

deep operator network (DeepONet)

Eikonal equation

randomized priors

tomography

uncertainty quantification

Details

Title: Subtitle: Uncertainty quantification for travel-time tomography using Deep Operator Networks with randomized priors
Creators: Yifan Mei - Xi'an Jiaotong University
Yijie Zhang - Xi'an Jiaotong University
Xueyu Zhu - University of Iowa
Jinghuai Gao - Xi'an Jiaotong University
Resource Type: Journal article
Publication Details: IEEE transactions on geoscience and remote sensing, Vol.63, pp.1-10
Publisher: IEEE
DOI: 10.1109/TGRS.2024.3524542
ISSN: 0196-2892
eISSN: 1558-0644
Grant note: National Natural Science Foundation of China: 42174137 Simons Foundation: MPS-TSM-00007740 National Key Research and Development Program of China: 2020YFA0713400
The work of Yifan Mei and Yijie Zhang was supported by the National Natural Science Foundation of China under Grant 42174137. The work of Xueyu Zhu was supported by the Simons Foundation under Grant MPS-TSM-00007740. The work of Jinghuai Gao was supported by the National Key Research and Development Program of China under Grant 2020YFA0713400.
Language: English
Electronic publication date: 2025
Date published: 2025
Academic Unit: Mathematics
Record Identifier: 9984770784602771

Metrics

3 Record Views