Showing papers in "Geophysics in 2021"
TL;DR: In this article, the determination of subsurface elastic property models is crucial in quantitative seismic data processing and interpretation, and this problem is commonly solved by deterministic physical meth-models.
Abstract: The determination of subsurface elastic property models is crucial in quantitative seismic data processing and interpretation. This problem is commonly solved by deterministic physical meth...
66 citations
TL;DR: In this article, an ensemble of convolutional neural networks (CNNs) was used to build velocity models of the subsurface in seismic imaging, which is the primary goal of seismic imaging.
Abstract: Building realistic and reliable models of the subsurface is the primary goal of seismic imaging. We have constructed an ensemble of convolutional neural networks (CNNs) to build velocity mo...
60 citations
TL;DR: In this article, full waveform inversion (FWI) can obtain the highest resolution in traditional velocity inversion methods, which is one of the most important tasks in seismic exploration.
Abstract: Velocity model inversion is one of the most important tasks in seismic exploration. Full-waveform inversion (FWI) can obtain the highest resolution in traditional velocity inversion methods...
54 citations
TL;DR: In this article, ground-penetrating radar is used to detect underground cavities under urban roads in order to improve traffic safety in many cities, such as New York and London.
Abstract: Cavities under urban roads have increasingly become a great threat to traffic safety in many cities. As a quick, effective, and high-resolution geophysical method, ground-penetrating radar ...
45 citations
TL;DR: In this paper, the misfit function of the conventional FWI method (metric l2-norm) was analyzed and it was shown that it is a powerful method for providing a high-resolution description of the subsurface.
Abstract: Full-waveform inversion (FWI) is a powerful method for providing a high-resolution description of the subsurface. However, the misfit function of the conventional FWI method (metric l2-norm...
38 citations
TL;DR: In this article, a deep neural network (DNN) is used to interpolate seismic data and obtain enough information for subsequent processing, which is an effective way of recovering missing traces.
Abstract: Seismic data interpolation is an effective way of recovering missing traces and obtaining enough information for subsequent processing. Unlike traditional methods, deep neural network (DNN)...
36 citations
TL;DR: This work has used the dropout approach, a regularization technique to prevent overfitting and coadaptation in hidden units, to approximate the Bayesian inference and estimate the principled uncertainty over functions.
Abstract: Segmentation of faults based on seismic images is an important step in reservoir characterization. With the recent developments of deep-learning methods and the availability of massive comp...
36 citations
TL;DR: A tutorial overview of two state-of-the-art ML implementations of classification and regression neural networks for the extraction of apparent rms velocity trajectories from semblance data.
Abstract: The physical basis, parameterization, and assumptions involved in root-mean-square (rms) velocity estimation have not significantly changed since they were first developed. However, these t...
34 citations
TL;DR: Seismic facies interpretation supports subsurface geologic environment analyses and reservoir predictions as discussed by the authors, and traditional interpretation methods require much manual work, and they heavily depepe...
Abstract: Seismic facies interpretation supports subsurface geologic environment analyses and reservoir predictions. Traditional interpretation methods require much manual work, and they heavily depe...
34 citations
TL;DR: In this article, full waveform inversion (FWI) is used for modeling velocity structure by minimizing the misfit between recorded and predicted seismic waveforms, but the strong non-line waveforms are not considered.
Abstract: Full-waveform inversion (FWI) is an accurate imaging approach for modeling velocity structure by minimizing the misfit between recorded and predicted seismic waveforms. However, the strong non-line...
33 citations
TL;DR: In this article, deep learning techniques applied to geophysical inverse problems have been applied to solve the inverse problem of the Geophysical Inverse Problem (GIP) in the field of geophysical engineering.
Abstract: Machine learning, and specifically deep-learning (DL) techniques applied to geophysical inverse problems, is an attractive subject, which has promising potential and, at the same time, pres...
TL;DR: In this paper, the authors proposed a deep learning-based method for seismic data interpolation with missing traces, which is a long-standing issue in seismic data processing and has emerged as a popular tool for seismic interpolation.
Abstract: The reconstruction of seismic data with missing traces has been a long-standing issue in seismic data processing. Deep learning (DL) has emerged as a popular tool for seismic interpolation;...
TL;DR: A prestack inversion algorithm that combines a discrete cosine transform (DCT) reparameterization of data and model spaces with a convolutional neural network (CNN) is developed, opening the possibility of estimating the subsurface elastic parameters and the associated uncertainties in near real time while satisfactorily preserving the assumed spatial variability and the statistical properties of the elastic parameters.
Abstract: We have developed a prestack inversion algorithm that combines a discrete cosine transform (DCT) reparameterization of data and model spaces with a convolutional neural network (CNN). The C...
TL;DR: In this paper, deep learning methods have shown promising performance in predicting acoustic impedance from seismic data that is typically considered as an ill-posed problem for traditional inversion-based inversion.
Abstract: Deep-learning (DL) methods have shown promising performance in predicting acoustic impedance from seismic data that is typically considered as an ill-posed problem for traditional inversion...
TL;DR: In this article, a high-resolution seismic imaging method is used for full waveform inversion, which is known to require sufficiently accurate initial models to converge toward meaningful estimations of the subsurface mecha.
Abstract: Full-waveform inversion, a high-resolution seismic imaging method, is known to require sufficiently accurate initial models to converge toward meaningful estimations of the subsurface mecha...
TL;DR: A Python framework is presented that leverages libraries for distributed storage and computing, and provides a high-level symbolic representation of linear operators, which highlights the memory requirements and computational challenges that arise when implementing such operators on 3D seismic datasets and their usage for solving large systems of integral equations.
Abstract: Numerical integral operators of the convolution type form the basis of most wave-equation-based methods for the processing and imaging of seismic data. Because several of these methods requ...
TL;DR: The different approaches to Marchenko redatuming, imaging and multiple elimination are discussed, using a common mathematical framework.
Abstract: With the Marchenko method, it is possible to retrieve Green’s functions between virtual sources in the subsurface and receivers at the surface from reflection data at the surface and focusi...
CGG1
TL;DR: In this article, the authors used full-wave-field data that includes primary reflections, transmitted waves, and their multiples for geophysics applications, such as seismic imaging.
Abstract: Seismic imaging using full-wavefield data that includes primary reflections, transmitted waves, and their multiples has been the holy grail for generations of geophysicists. To be able to ...
TL;DR: Geotechnical characterization of marine sediments remains an outstanding challenge for offshore energy development, including foundation design and site selection of wind turbines and offloading of offshore energy projects as discussed by the authors.
Abstract: Geotechnical characterization of marine sediments remains an outstanding challenge for offshore energy development, including foundation design and site selection of wind turbines and offs...
TL;DR: Horizontal layered formations with a suite of vertical or near-vertical fractures are usually assumed to be an approximate orthotropic medium and are more suitable for estimating fracture p... as mentioned in this paper.
Abstract: Horizontal layered formations with a suite of vertical or near-vertical fractures are usually assumed to be an approximate orthotropic medium and are more suitable for estimating fracture p...
TL;DR: In this article, the authors predict the distribution of fluid and lithofacies distribution in reservoir characterization, geologic model building, and flow unit delineation, using seismic data from the seafloor.
Abstract: Seismic prediction of fluid and lithofacies distribution is of great interest to reservoir characterization, geologic model building, and flow unit delineation. Inferring fluids and lithofa...
TL;DR: This work extends the regularized nonstationary autoregression (RNAR) method to the more general case, in which it can apply more constraints to the filter coefficients according to the features of seismic data, and applies a frequency-dependent smoothing radius in the spatial dimension to better deal with noise.
Abstract: Predictive filtering (PF) in the frequency domain is one of the most widely used denoising algorithms in seismic data processing. PF is based on the assumption of linear or planar events in...
TL;DR: The method aims at producing an effective low-rank filter and, thus, can perfectly enhance the S/N of the simultaneously denoised and reconstructed results with higher accuracy.
Abstract: We have developed a new method for simultaneous denoising and reconstruction of 5D seismic data corrupted by random noise and missing traces. Several algorithms have been developed for seis...
TL;DR: Sedimentary rocks are often heterogeneous porous media inherently containing complex distributions of heterogeneities (e.g., fluid patches and cracks). Understanding and modeling their freq... as mentioned in this paper.
Abstract: Sedimentary rocks are often heterogeneous porous media inherently containing complex distributions of heterogeneities (e.g., fluid patches and cracks). Understanding and modeling their freq...
TL;DR: Elastic properties from seismic data are important to determine subsurface hydrocarbon presence and have become increasingly important for detailed reservoir characterization that aids to the characterization of underground hydrocarbons.
Abstract: Elastic properties from seismic data are important to determine subsurface hydrocarbon presence and have become increasingly important for detailed reservoir characterization that aids to ...
TL;DR: A Bayesian neural network is introduced in quantitative log prediction studies with the goal of improving the petrophysical characterization and quantifying the uncertainty of model predictions and offers additional information on the confidence in the predictions.
Abstract: We have introduced a Bayesian neural network in quantitative log prediction studies with the goal of improving the petrophysical characterization and quantifying the uncertainty of model pr...
TL;DR: The synthetic numerical experiments suggest that the LF data predicted by the progressive transfer learning are sufficiently accurate for an FWI engine to produce reliable subsurface velocity models free of cycle-skipping artifacts.
Abstract: To effectively overcome the cycle-skipping issue in full-waveform inversion (FWI), we have developed a deep neural network (DNN) approach to predict the absent low-frequency (LF) components
TL;DR: An optimization-inspired deep learning inversion solver is proposed to solve the blind high-resolution inverse (BHRI) problems of various seismic wavelets rapidly, called BHRI-Net, and it makes full use of prior information encoded in the forward operator and noise model to learn an accurate mapping relationship.
Abstract: Seismic high-resolution processing plays a critical role in reservoir target detection. As one of the most common approaches, regularization can achieve a high-resolution inversion result. ...
TL;DR: In this paper, distributed acoustic sensing (DAS) has been applied to shallow seismic structure imaging providing dense spatial sampling at a relatively low cost. DAS on a standard straight fibres.
Abstract: Recently, distributed acoustic sensing (DAS) has been applied to shallow seismic structure imaging providing dense spatial sampling at a relatively low cost. DAS on a standard straight fibe...
TL;DR: In this article, a vertical seismic profiling (VSP) survey using VSP was conducted to optimize well spacings and completions for the development of unconventional reservoirs. But, the VSP survey was conducted in a non-cooperative manner.
Abstract: Optimization of well spacings and completions are key topics in research related to the development of unconventional reservoirs. In 2017, a vertical seismic profiling (VSP) survey using fi...