Show simple item record

dc.contributor.authorWaheed, Umair bin
dc.contributor.authorAlkhalifah, Tariq Ali
dc.contributor.authorHaghighat, Ehsan
dc.contributor.authorSong, Chao
dc.contributor.authorVirieux, Jean
dc.date.accessioned2021-04-12T06:26:53Z
dc.date.available2021-04-12T06:26:53Z
dc.date.issued2021-04-04
dc.identifier.urihttp://hdl.handle.net/10754/668666
dc.description.abstractSeismic traveltime tomography using transmission data is widely used to image the Earth's interior from global to local scales. In seismic imaging, it is used to obtain velocity models for subsequent depth-migration or full-waveform inversion. In addition, cross-hole tomography has been successfully applied for a variety of applications, including mineral exploration, reservoir monitoring, and CO2 injection and sequestration. Conventional tomography techniques suffer from a number of limitations, including the use of a smoothing regularizer that is agnostic to the physics of wave propagation. Here, we propose a novel tomography method to address these challenges using developments in the field of scientific machine learning. Using seismic traveltimes observed at seismic stations covering part of the computational model, we train neural networks to approximate the traveltime factor and the velocity fields, subject to the physics-informed regularizer formed by the factored eikonal equation. This allows us to better compensate for the ill-posedness of the tomography problem compared to conventional methods and results in a number of other attractive features, including computational efficiency. We show the efficacy of the proposed method and its capabilities through synthetic tests for surface seismic and cross-hole geometries. Contrary to conventional techniques, we find the performance of the proposed method to be agnostic to the choice of the initial velocity model.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2104.01588.pdf
dc.rightsArchived with thanks to arXiv
dc.subjectTomography
dc.subjectInversion
dc.subjectTraveltimes
dc.subjectNeural networks
dc.subjectMachine learning
dc.titlePINNtomo: Seismic tomography using physics-informed neural networks
dc.typePreprint
dc.contributor.departmentEarth Science and Engineering Program
dc.contributor.departmentPhysical Science and Engineering (PSE) Division
dc.contributor.departmentSeismic Wave Analysis Group
dc.eprint.versionPre-print
dc.contributor.institutionDepartment of Geosciences King Fahd University of Petroleum and Minerals Dhahran 31261, Saudi Arabia
dc.contributor.institutionDepartment of Civil Engineering Massachusetts Institute of Technology MA 02139, USA
dc.contributor.institutionISTERRE Université Grenoble Alpes Saint-Martin-d’Heres 38400, France
dc.identifier.arxivid2104.01588
kaust.personAlkhalifah, Tariq Ali
kaust.personSong, Chao
refterms.dateFOA2021-04-12T06:28:10Z


Files in this item

Thumbnail
Name:
2104.01588.pdf
Size:
430.4Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record