scholarly journals Regularized elastic full-waveform inversion using deep learning

Geophysics ◽  
2019 ◽  
Vol 84 (5) ◽  
pp. R741-R751 ◽  
Author(s):  
Zhen-Dong Zhang ◽  
Tariq Alkhalifah
Keyword(s):  
Deep Learning ◽  
Seismic Data ◽  
Prior Information ◽  
Waveform Inversion ◽  
Full Waveform Inversion ◽  
Multidimensional Distribution ◽  
Full Waveform ◽  
The Earth ◽  
Geophysical Surveys ◽  
High Resolution Models

Obtaining high-resolution models of the earth, especially around the reservoir, is crucial to properly image and interpret the subsurface. We have developed a regularized elastic full-waveform inversion (FWI) method that uses facies as the prior information. Deep neural networks (DNNs) are trained to estimate the distribution of facies in the subsurface. Here, we use facies extracted from wells as the prior information. Seismic data, well logs, and interpreted facies have different resolution and illumination to the subsurface. Besides, a physical process, such as anelasticity in the subsurface, is often too complicated to be fully considered. Therefore, there are often no explicit formulas to connect the data coming from different geophysical surveys. A deep-learning method can find the statistically correct connection without the need to know the complex physics. In our deep-learning scheme, we specifically use it to assist the inverse problem instead of the widely used labeling task. First, we conduct an adaptive data-selection elastic FWI using the observed seismic data and obtain estimates of the subsurface, which do not need to be perfect. Then, we use the extracted facies information from the wells and force the estimated model to fit the facies by training DNNs. In this way, a list of facies is mapped to a 2D or 3D inverted model guided mainly by the structure features of the model. The multidimensional distribution of facies is used either as a regularization term or as an initial model for the next waveform inversion. Our method has two main features: (1) It applies to any kind of distribution of data samples and (2) it interpolates facies between wells guided by the structure of the estimated models. Results with synthetic and field data illustrate the benefits and limitations of this method.

Data-driven low-frequency signal recovery using deep-learning predictions in full-waveform inversion

Geophysics ◽  
2020 ◽  
Vol 85 (6) ◽  
pp. A37-A43
Author(s):  
Jinwei Fang ◽  
Hui Zhou ◽  
Yunyue Elita Li ◽  
Qingchen Zhang ◽  
Lingqian Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Seismic Data ◽  
High Frequency ◽  
Waveform Inversion ◽  
Low Frequency ◽  
Data Driven ◽  
Full Waveform Inversion ◽  
Frequency Data ◽  
Recovery Method ◽  
Full Waveform

The lack of low-frequency signals in seismic data makes the full-waveform inversion (FWI) procedure easily fall into local minima leading to unreliable results. To reconstruct the missing low-frequency signals more accurately and effectively, we have developed a data-driven low-frequency recovery method based on deep learning from high-frequency signals. In our method, we develop the idea of using a basic data patch of seismic data to build a local data-driven mapping in low-frequency recovery. Energy balancing and data patches are used to prepare high- and low-frequency data for training a convolutional neural network (CNN) to establish the relationship between the high- and low-frequency data pairs. The trained CNN then can be used to predict low-frequency data from high-frequency data. Our CNN was trained on the Marmousi model and tested on the overthrust model, as well as field data. The synthetic experimental results reveal that the predicted low-frequency data match the true low-frequency data very well in the time and frequency domains, and the field results show the successfully extended low-frequency spectra. Furthermore, two FWI tests using the predicted data demonstrate that our approach can reliably recover the low-frequency data.

Target-oriented time-lapse elastic full-waveform inversion assisted by deep learning with prior information

2021 ◽  
Author(s):  
Yuanyuan Li ◽  
Andrey Bakulin ◽  
Philippe Nivlet ◽  
Robert Smith ◽  
Tariq Alkhalifah
Keyword(s):  
Deep Learning ◽  
Prior Information ◽  
Waveform Inversion ◽  
Time Lapse ◽  
Full Waveform Inversion ◽  
Full Waveform

Defining the Green’s function derivative for imaging & inversion without the Born approximation

2020 ◽  
Author(s):  
Dominic Cummings ◽  
Andrew Curtis
Keyword(s):  
Seismic Data ◽  
Born Approximation ◽  
Waveform Inversion ◽  
Single Scattering ◽  
Acoustic Medium ◽  
Full Waveform Inversion ◽  
Full Waveform ◽  
The Earth ◽  
Recent Emergence ◽  
And Inversion

<p>The goal of most seismic experiments is to use data readily available at the surface of the Earth to characterise the inaccessible interior. In order to solve this inverse problem, we generally make a number of assumptions about either the data or the Earth to simplify the physics. For example, we often assume that the Earth is an acoustic medium rather than an elastic medium, which for data without S-waves makes the problem far more tractable computationally than the full elastic problem.</p><p>One of the most common assumptions made about the data is the single-scattering assumption, widely known as the Born approximation. Clearly this is invalid in the presence of multiple scattering, which occurs in all seismic experiments. Despite this, the majority of imaging and inversion methods applied to seismic data are dependent on this assumption, including most full waveform inversion algorithms. As a consequence, seismic data processing requires a great deal of effort to remove multiply scattered waves from data.</p><p>A key justification for making this assumption is that a priori we can only estimate a relatively smooth Earth model that does not predict multiply scattered waves. However, with the recent emergence of so-called Marchenko methods, we now have access to full Green’s functions between sources and receivers at the Earth’s surface and virtual source or receiver locations inside the Earth’s interior, Green’s functions which can be estimated using only recorded reflection data and an estimate of the direct (non-scattered) wavefield travelling into the subsurface. As Marchenko methods become more commonplace, our justification for the single-scattering assumption diminishes, and hence we require new methods to use this information.</p><p>By iterating the Lippmann-Schwinger equation, we define a new compact form of the Frechét derivative of the Green’s function that involves all orders of scattering. In combination with Green’s functions obtained by a Marchenko method, these may be used for imaging and inversion of seismic data. We will describe an example of such a scheme, which we call “Marchenko Lippmann-Schwinger Full-Waveform Inversion”, to demonstrate how our redefined Green’s function derivative may be applied to solve seismic inverse problems for the Earth’s subsurface structure.</p>

scholarly journals High-resolution reservoir characterization using deep learning-aided elastic full-waveform inversion: The North Sea field data example

Geophysics ◽  
2020 ◽  
Vol 85 (4) ◽  
pp. WA137-WA146
Author(s):  
Zhen-dong Zhang ◽  
Tariq Alkhalifah
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
North Sea ◽  
Seismic Data ◽  
Field Data ◽  
Reservoir Characterization ◽  
Waveform Inversion ◽  
Oil Field ◽  
Full Waveform Inversion ◽  
Full Waveform

Reservoir characterization is an essential component of oil and gas production, as well as exploration. Classic reservoir characterization algorithms, deterministic and stochastic, are typically based on stacked images and rely on simplifications and approximations to the subsurface (e.g., assuming linearized reflection coefficients). Elastic full-waveform inversion (FWI), which aims to match the waveforms of prestack seismic data, potentially provides more accurate high-resolution reservoir characterization from seismic data. However, FWI can easily fail to characterize deep-buried reservoirs due to illumination limitations. We have developed a deep learning-aided elastic FWI strategy using observed seismic data and available well logs in the target area. Five facies are extracted from the well and then connected to the inverted P- and S-wave velocities using trained neural networks, which correspond to the subsurface facies distribution. Such a distribution is further converted to the desired reservoir-related parameters such as velocities and anisotropy parameters using a weighted summation. Finally, we update these estimated parameters by matching the resulting simulated wavefields to the observed seismic data, which corresponds to another round of elastic FWI aided by the a priori knowledge gained from the predictions of machine learning. A North Sea field data example, the Volve Oil Field data set, indicates that the use of facies as prior knowledge helps resolve the deep-buried reservoir target better than the use of only seismic data.

scholarly journals Full-Waveform Inversion for Imaging Faulted Structures: A Case Study from the Japan Trench Forearc Slope

2021 ◽  
Author(s):  
Ehsan Jamali Hondori ◽  
Chen Guo ◽  
Hitoshi Mikada ◽  
Jin-Oh Park
Keyword(s):  
Seismic Data ◽  
Initial Velocity ◽  
Waveform Inversion ◽  
Velocity Model ◽  
Control Measures ◽  
Japan Trench ◽  
Full Waveform Inversion ◽  
Full Waveform ◽  
Time Migration ◽  
Shallow Sediments

AbstractFull-waveform inversion (FWI) of limited-offset marine seismic data is a challenging task due to the lack of refracted energy and diving waves from the shallow sediments, which are fundamentally required to update the long-wavelength background velocity model in a tomographic fashion. When these events are absent, a reliable initial velocity model is necessary to ensure that the observed and simulated waveforms kinematically fit within an error of less than half a wavelength to protect the FWI iterative local optimization scheme from cycle skipping. We use a migration-based velocity analysis (MVA) method, including a combination of the layer-stripping approach and iterations of Kirchhoff prestack depth migration (KPSDM), to build an accurate initial velocity model for the FWI application on 2D seismic data with a maximum offset of 5.8 km. The data are acquired in the Japan Trench subduction zone, and we focus on the area where the shallow sediments overlying a highly reflective basement on top of the Cretaceous erosional unconformity are severely faulted and deformed. Despite the limited offsets available in the seismic data, our carefully designed workflow for data preconditioning, initial model building, and waveform inversion provides a velocity model that could improve the depth images down to almost 3.5 km. We present several quality control measures to assess the reliability of the resulting FWI model, including ray path illuminations, sensitivity kernels, reverse time migration (RTM) images, and KPSDM common image gathers. A direct comparison between the FWI and MVA velocity profiles reveals a sharp boundary at the Cretaceous basement interface, a feature that could not be observed in the MVA velocity model. The normal faults caused by the basal erosion of the upper plate in the study area reach the seafloor with evident subsidence of the shallow strata, implying that the faults are active.

scholarly journals Adding Prior Information in FWI through Relative Entropy

Entropy ◽  
2021 ◽  
Vol 23 (5) ◽  
pp. 599
Author(s):  
Danilo Cruz ◽  
João de Araújo ◽  
Carlos da Costa ◽  
Carlos da Silva
Keyword(s):  
Inverse Problem ◽  
Relative Entropy ◽  
Global Minimum ◽  
Prior Information ◽  
Waveform Inversion ◽  
Petroleum Industry ◽  
Synthetic Data ◽  
Full Waveform Inversion ◽  
Full Waveform

Full waveform inversion is an advantageous technique for obtaining high-resolution subsurface information. In the petroleum industry, mainly in reservoir characterisation, it is common to use information from wells as previous information to decrease the ambiguity of the obtained results. For this, we propose adding a relative entropy term to the formalism of the full waveform inversion. In this context, entropy will be just a nomenclature for regularisation and will have the role of helping the converge to the global minimum. The application of entropy in inverse problems usually involves formulating the problem, so that it is possible to use statistical concepts. To avoid this step, we propose a deterministic application to the full waveform inversion. We will discuss some aspects of relative entropy and show three different ways of using them to add prior information through entropy in the inverse problem. We use a dynamic weighting scheme to add prior information through entropy. The idea is that the prior information can help to find the path of the global minimum at the beginning of the inversion process. In all cases, the prior information can be incorporated very quickly into the full waveform inversion and lead the inversion to the desired solution. When we include the logarithmic weighting that constitutes entropy to the inverse problem, we will suppress the low-intensity ripples and sharpen the point events. Thus, the addition of entropy relative to full waveform inversion can provide a result with better resolution. In regions where salt is present in the BP 2004 model, we obtained a significant improvement by adding prior information through the relative entropy for synthetic data. We will show that the prior information added through entropy in full-waveform inversion formalism will prove to be a way to avoid local minimums.

scholarly journals Multi-scale time-frequency domain full waveform inversion with a weighted local correlation-phase misfit function

2019 ◽  
Vol 16 (6) ◽  
pp. 1017-1031 ◽  
Author(s):  
Yong Hu ◽  
Liguo Han ◽  
Rushan Wu ◽  
Yongzhong Xu
Keyword(s):  
Frequency Domain ◽  
Seismic Data ◽  
Waveform Inversion ◽  
Low Frequency ◽  
Full Waveform Inversion ◽  
Local Correlation ◽  
Time Frequency ◽  
Model Dependence ◽  
Full Waveform ◽  
Frequency Components

Abstract Full Waveform Inversion (FWI) is based on the least squares algorithm to minimize the difference between the synthetic and observed data, which is a promising technique for high-resolution velocity inversion. However, the FWI method is characterized by strong model dependence, because the ultra-low-frequency components in the field seismic data are usually not available. In this work, to reduce the model dependence of the FWI method, we introduce a Weighted Local Correlation-phase based FWI method (WLCFWI), which emphasizes the correlation phase between the synthetic and observed data in the time-frequency domain. The local correlation-phase misfit function combines the advantages of phase and normalized correlation function, and has an enormous potential for reducing the model dependence and improving FWI results. Besides, in the correlation-phase misfit function, the amplitude information is treated as a weighting factor, which emphasizes the phase similarity between synthetic and observed data. Numerical examples and the analysis of the misfit function show that the WLCFWI method has a strong ability to reduce model dependence, even if the seismic data are devoid of low-frequency components and contain strong Gaussian noise.

Sign in / Sign up

Export Citation Format

Share Document