Waveform inversion of poststacked reflection seismic data with well log constrained using nonlinear optimization methods

Parra, Jorge O.; Parra, Jonathan S.; Iturrarán-Viveros, Ursula

doi:10.1190/tle36121032a1.1

Cited by 4 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Final inversion velocity model V p obtained from the initial Vp calculated via the P-wave impedance Figure 11 Initial velocity model V p obtained using a Broyden-Fletcher-Goldfarb-Shanno neural network Machine Learning as a Seismic Prior Velocity Model Building Method least-squares curve fitting between the synthetic and observed seismograms. This approach is similar to that given in Parra et al (2017Parra et al ( , 2019. Waveform inversion via nonlinear least-squares minimization is effective when the starting model is accurate (Tarantola and Valette 1982).…”

Section: Figure 10mentioning

confidence: 97%

“…Deriving impedance values from seismic data can be done using the band-limited impedance inversion method (BLIMP) described in Ferguson and Margrave (1996) and Maulana et al (2016). This method was also successfully applied in Parra et al (2017). One disadvantage of the method is that it requires the information of density in the interval of the impedance inversion.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning as a Seismic Prior Velocity Model Building Method for Full-Waveform Inversion: A Case Study from Colombia

Iturrarán-Viveros

Muñoz-García

Castillo-Reyes

et al. 2021

Pure Appl. Geophys.

View full text Add to dashboard Cite

We use machine learning algorithms (artificial neural networks, ANNs) to estimate petrophysical models at seismic scale combining well-log information, seismic data and seismic attributes. The resulting petrophysical images are the prior inputs in the process of full-waveform inversion (FWI). We calculate seismic attributes from a stacked reflected 2-D seismic section and then train ANNs to approximate the following petrophysical parameters: P-wave velocity ($$V_\mathrm{{p}}$$ V p ), density ($$\rho $$ ρ ) and volume of clay ($$V_\mathrm{{clay}}$$ V clay ). We extend the use of the $$V_\mathrm{{clay}}$$ V clay by constraining it with the well lithology and we establish two classes: sands and shales. Consequently, machine learning allows us to build an initial estimate of the earth property model ($$V_\mathrm{{p}}$$ V p ), which is iteratively refined to produce a synthetic seismogram that matches the observed seismic data. We apply the 1-D Kennett method as a forward modeling tool to create synthetic data with the images of $$V_\mathrm{{p}}$$ V p , $$\rho $$ ρ and the thickness of layers (sands or shales) obtained with the ANNs. A nonlinear least-squares inversion algorithm minimizes the residual (or misfit) between observed and synthetic full-waveform data, which improves the $$V_\mathrm{{p}}$$ V p resolution. In order to show the advantage of using the ANN velocity model as the initial velocity model for the inversion, we compare the results obtained with the ANNs and two other initial velocity models. One of these alternative initial velocity models is computed via P-wave impedance, and the other is achieved by velocity semblance analysis: root-mean-square velocity (RMS). The results are in good agreement when we use $$\rho $$ ρ and $$V_\mathrm{{p}}$$ V p obtained by ANNs. However, the results are poor and the synthetic data do not match the real acquired data when using the semblance velocity model and the $$\rho $$ ρ from the well log (constant for the entire 2-D section). Nevertheless, the results improve when including $$\rho $$ ρ , the layered structure driven by the $$V_\mathrm{{clay}}$$ V clay (both obtained with ANNs) and the semblance velocity model. When doing inversion starting with the initial $$V_\mathrm{{p}}$$ V p model estimated using the P-wave impedance, there is some gain of the final $$V_\mathrm{{p}}$$ V p with respect to the RMS initial $$V_\mathrm{{p}}$$ V p . To assess the quality of the inversion of $$V_\mathrm{{p}}$$ V p , we use the information for two available wells and compare the final $$V_\mathrm{{p}}$$ V p obtained with ANNs and the final $$V_\mathrm{{p}}$$ V p computed with the P-wave impedance. This shows the benefit of employing ANNs estimations as prior models during the inversion process to obtain a final $$V_\mathrm{{p}}$$ V p that is in agreement with the geology and with the seismic and well-log data. To illustrate the computation of the final velocity model via FWI, we provide an algorithm with the detailed steps and its corresponding GitHub code.

show abstract

Section: Figure 10mentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Machine Learning as a Seismic Prior Velocity Model Building Method for Full-Waveform Inversion: A Case Study from Colombia

Iturrarán-Viveros

Muñoz-García

Castillo-Reyes

et al. 2021

Pure Appl. Geophys.

View full text Add to dashboard Cite

show abstract

Petrophysical seismic images obtained with artificial neural networks as prior models for full-waveform inversion: A case study from Colombia

Iturrarán-Viveros

Muñoz-García

Parra³

2018

SEG Technical Program Expanded Abstracts 2018

View full text Add to dashboard Cite

Nonlinear inversion of subsidence signatures induced by tunnels detected with surface and remote sensing measurements

Parra¹,

Parra²,

Necsoiu

2019

The Leading Edge

View full text Add to dashboard Cite

The state of the art in predicting tunnel-induced subsidence settlements is based on empirical and analytical methods. Empirical methods are useful when the equations are implemented with host medium properties where tunnels have been excavated. Analytical solutions can predict tunneling-induced ground movements, with the predictions accounting for tunnel radius and depth as well as ground-loss parameters in soft soils. The drawback is that these methods require human intervention, as each model must be adjusted manually by the interpreter until the model signature fits the observed data. It would take tremendous effort to evaluate displacement anomalies detected by remote sensing methods using such forward-modeling methods. Therefore, we present a method based on an inversion algorithm that automatically inverts subsidence signatures for tunnel radius, depth, Poisson's ratio, and the gap parameter. It is an advancement over conventional methods because it does not require a first guess, and it can invert several subsidence signatures in a matter of minutes. The algorithm, coupled with remote sensing-based displacement maps, is a cost-effective solution in operational characterization of displacement anomalies. We demonstrate that observed and predicted subsidence signatures are in good agreement with existing tunnel data in uniform clay and that the inversion parameters correspond to those predicted with forward modeling alone.

show abstract

Waveform inversion of poststacked reflection seismic data with well log constrained using nonlinear optimization methods

Cited by 4 publications

References 3 publications

Machine Learning as a Seismic Prior Velocity Model Building Method for Full-Waveform Inversion: A Case Study from Colombia

Machine Learning as a Seismic Prior Velocity Model Building Method for Full-Waveform Inversion: A Case Study from Colombia

Petrophysical seismic images obtained with artificial neural networks as prior models for full-waveform inversion: A case study from Colombia

Nonlinear inversion of subsidence signatures induced by tunnels detected with surface and remote sensing measurements

Contact Info

Product

Resources

About