Stochastic seismic waveform inversion using generative adversarial networks as a geological prior

L Mosser, O Dubrule, MJ Blunt - Mathematical Geosciences, 2020 - Springer
We present an application of deep generative models in the context of partial differential
equation constrained inverse problems. We combine a generative adversarial network …

[HTML][HTML] Devito (v3. 1.0): an embedded domain-specific language for finite differences and geophysical exploration

M Louboutin, M Lange, F Luporini… - Geoscientific Model …, 2019 - gmd.copernicus.org
We introduce Devito, a new domain-specific language for implementing high-performance
finite-difference partial differential equation solvers. The motivating application is exploration …

A large-scale framework for symbolic implementations of seismic inversion algorithms in Julia

PA Witte, M Louboutin, N Kukreja, F Luporini, M Lange… - Geophysics, 2019 - library.seg.org
Writing software packages for seismic inversion is a very challenging task because
problems such as full-waveform inversion or least-squares imaging are algorithmically and …

Near-surface 2D imaging via FWI of DAS data: An examination on the impacts of FWI starting model

MBS Yust, BR Cox, JP Vantassel, PG Hubbard… - Geosciences, 2023 - mdpi.com
Full waveform inversion (FWI) and distributed acoustic sensing (DAS) are powerful tools with
potential to improve how seismic site characterization is performed. FWI is able to provide …

An event-driven approach to serverless seismic imaging in the cloud

PA Witte, M Louboutin, H Modzelewski… - … on Parallel and …, 2020 - ieeexplore.ieee.org
Adapting the cloud for high-performance computing (HPC) is a challenging task, as software
for HPC applications hinges on fast network connections and is sensitive to hardware …

Compressive least-squares migration with on-the-fly Fourier transforms

PA Witte, M Louboutin, F Luporini, GJ Gorman… - Geophysics, 2019 - library.seg.org
Least-squares reverse time migration is a powerful approach for true-amplitude seismic
imaging of complex geologic structures, but the successful application of this method is …

Projection methods and applications for seismic nonlinear inverse problems with multiple constraints

B Peters, BR Smithyman, FJ Herrmann - Geophysics, 2019 - library.seg.org
Nonlinear inverse problems are often hampered by local minima because of missing low
frequencies and far offsets in the data, lack of access to good starting models, noise, and …

Synthetic data generation for deep learning-based inversion for velocity model building

A Parasyris, L Stankovic, V Stankovic - Remote Sensing, 2023 - mdpi.com
Recent years have seen deep learning (DL) architectures being leveraged for learning the
nonlinear relationships across the parameters in seismic inversion problems in order to …

Full waveform inversion-based ultrasound computed tomography acceleration using two-dimensional convolutional neural networks

C Kleman, S Anwar, Z Liu… - Journal of …, 2023 - asmedigitalcollection.asme.org
Ultrasound computed tomography (USCT) shows great promise in nondestructive
evaluation and medical imaging due to its ability to quickly scan and collect data from a …

A note on extended full waveform inversion

T van Leeuwen - arxiv preprint arxiv:1904.00363, 2019 - arxiv.org
Full waveform inversion (FWI) aims at estimating subsurface medium properties from
measured seismic data. It is usually cast as a non-linear least-squares problem that …