Efficient Wavefield Inversion With Outer Iterations and Total Variation Constraint

IEEE Trans. Geosci. Remote Sensing

2022

Self Cite

Wavefield reconstruction inversion (WRI) formulates a PDE-constrained optimization problem to reduce cycle skipping in full-waveform inversion (FWI). WRI is often implemented by solving for the frequency-domain representation of the wavefield using the finite-difference method. The approach requires matrix inversions and affords limited flexibility to accommodating irregular model geometries. On the other hand, physics-informed neural network (PINN) uses the underlying physical laws as loss functions to train the neural network (NN) to provide flexible continuous functional approximations of the solutions without matrix inversions. By including a dataconstrained term in the loss function, the trained NN can reconstruct a wavefield that simultaneously fits the recorded data and satisfies the Helmholtz equation for a given initial velocity model. Using the predicted wavefields, we rely on a small-size NN to predict the velocity using the reconstructed wavefield. In this velocity prediction NN, spatial coordinates are used as input data to the network and the scattered Helmholtz equation is used to define the loss function. After we train this network, we are able to predict the velocity in the domain of interest. We develop this PINN-based WRI method and demonstrate its potential using a part of the Sigsbee2A model and a modified Marmousi model. The results show that the PINN-based WRI is able to invert for a reasonable velocity with very limited iterations and frequencies, which can be used in a subsequent FWI application.

Section: Introductionmentioning

confidence: 99%

Wavefield Reconstruction Inversion via Physics-Informed Neural Networks

Song

IEEE Trans. Geosci. Remote Sensing

2022

Self Cite

“…After decades of development, the FWI theory has been widely migrated to recover density, impedance, and anisotropy parameters [1]- [4]; or map the permittivity and conductivity distributions in the Earth's interior [5]- [7]. However, as a strongly nonlinear inverse problem, FWI usually suffers from the cycle-skipping problem when initial models are crude and low-frequency components of the data are unavailable [8]- [11].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Low-Wavenumber Information in Reflection Waveform Inversion by the Energy Norm Born Scattering

Wang

IEEE Geosci. Remote Sensing Lett.

Wang

2022

Full waveform inversion (FWI) plays a central role in the field of exploration geophysics due to its potential in recovering the properties of the subsurface at a high resolution. A starting model with ample long-wavelength components is essential for the success of most FWI algorithms. Reflection waveform inversion (RWI) is one popular way to invert for the long-wavelength velocity components from the short offset seismic data by decomposing the gradient of FWI into migration and tomographic terms. However, the transmitted part of Born scattering in conventional RWI still produces high-wavenumber artifacts, which would hinder its convergence. Thus, in this letter, an efficient non-transmission energy norm Born scattering is used in RWI to overcome the drawbacks of conventional RWI. Finally, we use numerical examples to show that the energy norm Born scattering can provide clean reflection energy from the reflector and enhance the low-wavenumber information in the RWI gradient.

“…Full waveform inversion (FWI) has emerged as a promising technique for retrieving subsurface properties by solving a data-driven optimization problem iteratively (Tarantola, 1984;Vigh et al, 2014;Choi and Alkhalifah, 2011;Li et al, 2018;Song and Alkhalifah, 2020). Time-lapse FWI is a straightforward extension of FWI to time-lapse seismic data and has gained considerable interest (Hicks et al, 2016;Kazei and Alkhalifah, 2018).…”

Section: Introductionmentioning

confidence: 99%

Target-oriented time-lapse waveform inversion using redatumed data: Feasibility and robustness

Guo

SEG Technical Program Expanded Abstracts 2020

et al. 2020

Seismic monitoring of the changes in the subsurface induced by various types of injections into reservoirs is important, yet challenging. Time-lapse waveform inversion can retrieve quantitative estimates of subsurface property changes. Considering that property changes usually occur in a limited region rather than the whole subsurface, we present a target-oriented time-lapse waveform inversion method, which allows for dynamic monitoring of the target of interest. We employ a redatuming technique to produce virtual data at a desired datum level for the target-oriented inversion. Given the redatumed time-lapse data, the property changes can be quantitatively estimated from the data difference for the virtual survey using a doubledifference waveform inversion (DDWI). In the numerical examples, the dependence of the inversion performance on the quality of overburden model and its robustness to nonrepeatable acquisition survey and random noise is investigated. The numerical results demonstrate that the inversion method is capable of recovering the time-lapse changes reasonably well under some challenging circumstances. We will show field data examples at the conference.