Salt delineation via interpreter-guided 3D seismic image segmentation

Although it is a crucial component of seismic velocity model building, salt delineation is often a major bottleneck in the interpretation workflow. Automatic methods like image segmentation can help to alleviate this bottleneck, but issues with accuracy and efficiency can hinder their effectiveness. However, a new graph-based segmentation algorithm can, after modifications to account for the unique nature of seismic data, quickly and accurately delineate salt bodies on 3D seismic images. In areas where salt boundaries are poorly imaged, limited manual interpretations can be used to guide the automatic segmentation, allowing for interpreter insight to be combined with modern computational capabilities. A successful 3D field data example demonstrates that this method could become an important tool for interactive interpretation tasks.

Download Full-text

Full Wavefield Redatuming: Accurate Velocity Modelling for Imaging Beneath Complex Overburden

10.2523/iptc-21771-ms ◽

2021 ◽

Author(s):

Farah Syazana Dzulkefli ◽

Kefeng Xin ◽

Ahmad Riza Ghazali ◽

Guo Qiang ◽

Tariq Alkhalifah

Keyword(s):

Wave Propagation ◽

Seismic Data ◽

Model Building ◽

Velocity Model ◽

Surrounding Rock ◽

Target Area ◽

Low Density ◽

Velocity Model Building ◽

Seismic Image ◽

Seismic Wavefield

Abstract Salt is known for having a generally low density and higher velocity compared with the surrounding rock layers which causes the energy to scatter once the seismic wavefield hits the salt body and relatively less energy is transmitted through the salt to the deeper subsurface. As a result, most of imaging approaches are unable to image the base of the salt and the reservoir below the salt. Even the velocity model building such as FWI often fails to illuminate the deeper parts of salt area. In this paper, we show that Full Wavefield Redatuming (FWR) is used to retrieved and enhance the seismic data below the salt area, leading to a better seismic image quality and allowing us to focus on updating the velocity in target area below the salt. However, this redatuming approach requires a good overburden velocity model to retrieved good redatumed data. Thus, by using synthetic SEAM model, our objective is to study on the accuracy of the overburden velocity model required for imaging beneath complex overburden. The results show that the kinematic components of wave propagation are preserved through redatuming even with heavily smoothed overburden velocity model.

Download Full-text

Seismic velocity estimation: A deep recurrent neural-network approach

Geophysics ◽

10.1190/geo2018-0786.1 ◽

2019 ◽

Vol 85 (1) ◽

pp. U21-U29

Author(s):

Gabriel Fabien-Ouellet ◽

Rahul Sarkar

Keyword(s):

Neural Network ◽

Neural Networks ◽

Recurrent Neural Networks ◽

Model Building ◽

Seismic Velocity ◽

Velocity Model ◽

Velocity Estimation ◽

Interval Velocity ◽

Velocity Model Building ◽

3D Velocity Model

Applying deep learning to 3D velocity model building remains a challenge due to the sheer volume of data required to train large-scale artificial neural networks. Moreover, little is known about what types of network architectures are appropriate for such a complex task. To ease the development of a deep-learning approach for seismic velocity estimation, we have evaluated a simplified surrogate problem — the estimation of the root-mean-square (rms) and interval velocity in time from common-midpoint gathers — for 1D layered velocity models. We have developed a deep neural network, whose design was inspired by the information flow found in semblance analysis. The network replaces semblance estimation by a representation built with a deep convolutional neural network, and then it performs velocity estimation automatically with recurrent neural networks. The network is trained with synthetic data to identify primary reflection events, rms velocity, and interval velocity. For a synthetic test set containing 1D layered models, we find that rms and interval velocity are accurately estimated, with an error of less than [Formula: see text] for the rms velocity. We apply the neural network to a real 2D marine survey and obtain accurate rms velocity predictions leading to a coherent stacked section, in addition to an estimation of the interval velocity that reproduces the main structures in the stacked section. Our results provide strong evidence that neural networks can estimate velocity from seismic data and that good performance can be achieved on real data even if the training is based on synthetics. The findings for the 1D problem suggest that deep convolutional encoders and recurrent neural networks are promising components of more complex networks that can perform 2D and 3D velocity model building.

Download Full-text

Application of the Rock Physics Model in Anisotropic Seismic Velocity Model Building and Quantitative Reservoir Structural Uncertainty Analysis: Gulf of Mexico Case Study

10.2523/iptc-16794-ms ◽

2013 ◽

Author(s):

Yi Yang ◽

Konstantin Osypov ◽

Ran Bachrach ◽

Dave Nichols ◽

Marta Woodward ◽

...

Keyword(s):

Gulf Of Mexico ◽

Model Building ◽

Seismic Velocity ◽

Rock Physics ◽

Velocity Model ◽

Structural Uncertainty ◽

Velocity Model Building ◽

Physics Model ◽

Rock Physics Model

Download Full-text

Seismic Velocity Model Building Using Neural Networks: Training Data Design and Learning Generalization

Geophysics ◽

10.1190/geo2020-0547.1 ◽

2021 ◽

pp. 1-73

Author(s):

Hani Alzahrani ◽

Jeffrey Shragge

Keyword(s):

Seismic Data ◽

Model Building ◽

Seismic Velocity ◽

Velocity Model ◽

Training Data ◽

Training Process ◽

Training Models ◽

Velocity Models ◽

Velocity Model Building ◽

Layer Velocity

Data-driven artificial neural networks (ANNs) offer a number of advantages over conventional deterministic methods in a wide range of geophysical problems. For seismic velocity model building, judiciously trained ANNs offer the possibility of estimating high-resolution subsurface velocity models. However, a significant challenge of ANNs is training generalization, which is the ability of an ANN to apply the learning from the training process to test data not previously encountered. In the context of velocity model building, this means learning the relationship between velocity models and the corresponding seismic data from a set of training data, and then using acquired seismic data to accurately estimate unknown velocity models. We ask the following question: what type of velocity model structures need be included in the training process so that the trained ANN can invert seismic data from a different (hypothetical) geological setting? To address this question, we create four sets of training models: geologically inspired and purely geometrical, both with and without background velocity gradients. We find that using geologically inspired training data produce models with well-delineated layer interfaces and fewer intra-layer velocity variations. The absence of a certain geological structure in training models, though, hinders the ANN's ability to recover it in the testing data. We use purely geometric training models consisting of square blocks of varying size to demonstrate the ability of ANNs to recover reasonable approximations of flat, dipping, and curved interfaces. However, the predicted models suffer from intra-layer velocity variations and non-physical artifacts. Overall, the results successfully demonstrate the use of ANNs in recovering accurate velocity model estimates, and highlight the possibility of using such an approach for the generalized seismic velocity inversion problem.

Download Full-text

Why FWI Isn’t the Only Answer in Seismic Velocity Model Building

10.3997/2214-4609.202012151 ◽

2020 ◽

Author(s):

J.T. Etgen

Keyword(s):

Model Building ◽

Seismic Velocity ◽

Velocity Model ◽

Velocity Model Building

Download Full-text

Deep-learning inversion: A next-generation seismic velocity model building method

Geophysics ◽

10.1190/geo2018-0249.1 ◽

2019 ◽

Vol 84 (4) ◽

pp. R583-R599 ◽

Cited By ~ 38

Author(s):

Fangshu Yang ◽

Jianwei Ma

Keyword(s):

Deep Learning ◽

Seismic Data ◽

Model Building ◽

Seismic Velocity ◽

Velocity Model ◽

Computational Time ◽

Learning Methods ◽

Velocity Models ◽

Velocity Model Building ◽

Training Stage

Seismic velocity is one of the most important parameters used in seismic exploration. Accurate velocity models are the key prerequisites for reverse time migration and other high-resolution seismic imaging techniques. Such velocity information has traditionally been derived by tomography or full-waveform inversion (FWI), which are time consuming and computationally expensive, and they rely heavily on human interaction and quality control. We have investigated a novel method based on the supervised deep fully convolutional neural network for velocity-model building directly from raw seismograms. Unlike the conventional inversion method based on physical models, supervised deep-learning methods are based on big-data training rather than prior-knowledge assumptions. During the training stage, the network establishes a nonlinear projection from the multishot seismic data to the corresponding velocity models. During the prediction stage, the trained network can be used to estimate the velocity models from the new input seismic data. One key characteristic of the deep-learning method is that it can automatically extract multilayer useful features without the need for human-curated activities and an initial velocity setup. The data-driven method usually requires more time during the training stage, and actual predictions take less time, with only seconds needed. Therefore, the computational time of geophysical inversions, including real-time inversions, can be dramatically reduced once a good generalized network is built. By using numerical experiments on synthetic models, the promising performance of our proposed method is shown in comparison with conventional FWI even when the input data are in more realistic scenarios. We have also evaluated deep-learning methods, the training data set, the lack of low frequencies, and the advantages and disadvantages of our method.

Download Full-text

Acquisition/Processing

The Leading Edge ◽

10.1190/tle40060460.1 ◽

2021 ◽

Vol 40 (6) ◽

pp. 460-463

Author(s):

Lionel J. Woog ◽

Anthony Vassiliou ◽

Rodney Stromberg

Keyword(s):

Model Building ◽

Seismic Velocity ◽

Signal To Noise Ratio ◽

Velocity Model ◽

High Signal ◽

Processing Unit ◽

High Quality ◽

Near Surface ◽

Velocity Model Building ◽

Static Corrections

In seismic data processing, static corrections for near-surface velocities are derived from first-break picking. The quality of the static corrections is paramount to developing an accurate shallow velocity model, a model that in turn greatly impacts the subsequent seismic processing steps. Because even small errors in first-break picking can greatly impact the seismic velocity model building, it is necessary to pick high-quality traveltimes. Whereas various artificial intelligence-based methods have been proposed to automate the process for data with medium to high signal-to-noise ratio (S/N), these methods are not applicable to low-S/N data, which still require intensive labor from skilled operators. We successfully replace 160 hours of skilled human work with 10 hours of processing by a single NVIDIA Quadro P6000 graphical processing unit by reducing the number of human picks from the usual 5%–10% to 0.19% of available gathers. High-quality inferred picks are generated by convolutional neural network-based machine learning trained from the human picks.

Download Full-text