Edge-aware filtering with Siamese neural networks

2020 ◽  
Vol 39 (10) ◽  
pp. 711-717
Author(s):  
Mehdi Aharchaou ◽  
Michael Matheney ◽  
Joe Molyneux ◽  
Erik Neumann
Keyword(s):  
Neural Networks ◽  
Seismic Data ◽  
Learning Ability ◽  
Seismic Exploration ◽  
Data Sets ◽  
3D Seismic ◽  
New Class ◽  
Seismic Image ◽  
Siamese Networks ◽  
Seismic Images

Recent demands to reduce turnaround times and expedite investment decisions in seismic exploration have invited new ways to process and interpret seismic data. Among these ways is a more integrated collaboration between seismic processors and geologist interpreters aiming to build preliminary geologic models for early business impact. A key aspect has been quick and streamlined delivery of clean high-fidelity 3D seismic images via postmigration filtering capabilities. We present a machine learning-based example of such a capability built on recent advances in deep learning systems. In particular, we leverage the power of Siamese neural networks, a new class of neural networks that is powerful at learning discriminative features. Our novel adaptation, edge-aware filtering, employs a deep Siamese network that ranks similarity between seismic image patches. Once the network is trained, we capitalize on the learned features and self-similarity property of seismic images to achieve within-image stacking power endowed with edge awareness. The method generalizes well to new data sets due to the few-shot learning ability of Siamese networks. Furthermore, the learning-based framework can be extended to a variety of noise types in 3D seismic data. Using a convolutional architecture, we demonstrate on three field data sets that the learned representations lead to superior filtering performance compared to structure-oriented filtering. We examine both filtering quality and ease of application in our analysis. Then, we discuss the potential of edge-aware filtering as a data conditioning tool for rapid structural interpretation.

Seismic fault detection with convolutional neural network

Geophysics ◽  
2018 ◽  
Vol 83 (5) ◽  
pp. O97-O103 ◽  
Author(s):  
Wei Xiong ◽  
Xu Ji ◽  
Yue Ma ◽  
Yuxiang Wang ◽  
Nasher M. AlBinHassan ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Field Data ◽  
Data Sets ◽  
3D Seismic ◽  
Learning Tools ◽  
Seismic Fault ◽  
Seismic Image ◽  
Coherence Estimation ◽  
Seismic Images

Mapping fault planes using seismic images is a crucial and time-consuming step in hydrocarbon prospecting. Conventionally, this requires significant manual efforts that normally go through several iterations to optimize how the different fault planes connect with each other. Many techniques have been developed to automate this process, such as seismic coherence estimation, edge detection, and ant-tracking, to name a few. However, these techniques do not take advantage of the valuable experience accumulated by the interpreters. We have developed a method that uses the convolutional neural network (CNN) to automatically detect and map fault zones using 3D seismic images in a similar fashion to the way done by interpreters. This new technique is implemented in two steps: training and prediction. In the training step, a CNN model is trained with annotated seismic image cubes of field data, where every point in the seismic image is labeled as fault or nonfault. In the prediction step, the trained model is applied to compute fault probabilities at every location in other seismic image cubes. Unlike reported methods in the literature, our technique does not require precomputed attributes to predict the faults. We verified our approach on the synthetic and field data sets. We clearly determined that the CNN-computed fault probability outperformed that obtained using the coherence technique in terms of exhibiting clearer discontinuities. With the capability of emulating human experience and evolving through training using new field data sets, deep-learning tools manifest huge potential in automating and advancing seismic fault mapping.

FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation

Geophysics ◽  
2019 ◽  
Vol 84 (3) ◽  
pp. IM35-IM45 ◽  
Author(s):  
Xinming Wu ◽  
Luming Liang ◽  
Yunzhi Shi ◽  
Sergey Fomel
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Convolutional Neural Network ◽  
Synthetic Data ◽  
Data Sets ◽  
3D Seismic ◽  
Fault Segmentation ◽  
Seismic Image ◽  
Conventional Methods ◽  
Seismic Images

Delineating faults from seismic images is a key step for seismic structural interpretation, reservoir characterization, and well placement. In conventional methods, faults are considered as seismic reflection discontinuities and are detected by calculating attributes that estimate reflection continuities or discontinuities. We consider fault detection as a binary image segmentation problem of labeling a 3D seismic image with ones on faults and zeros elsewhere. We have performed an efficient image-to-image fault segmentation using a supervised fully convolutional neural network. To train the network, we automatically create 200 3D synthetic seismic images and corresponding binary fault labeling images, which are shown to be sufficient to train a good fault segmentation network. Because a binary fault image is highly imbalanced between zeros (nonfault) and ones (fault), we use a class-balanced binary cross-entropy loss function to adjust the imbalance so that the network is not trained or converged to predict only zeros. After training with only the synthetic data sets, the network automatically learns to calculate rich and proper features that are important for fault detection. Multiple field examples indicate that the neural network (trained by only synthetic data sets) can predict faults from 3D seismic images much more accurately and efficiently than conventional methods. With a TITAN Xp GPU, the training processing takes approximately 2 h and predicting faults in a [Formula: see text] seismic volume takes only milliseconds.

scholarly journals Appraising structural interpretations using seismic data — Theoretical elements

Geophysics ◽  
2019 ◽  
Vol 84 (2) ◽  
pp. N29-N40
Author(s):  
Modeste Irakarama ◽  
Paul Cupillard ◽  
Guillaume Caumon ◽  
Paul Sava ◽  
Jonathan Edwards
Keyword(s):  
Seismic Data ◽  
Structural Model ◽  
Synthetic Data ◽  
Target Region ◽  
Structural Interpretation ◽  
Vertical Seismic Profiling ◽  
Seismic Image ◽  
Vsp Data ◽  
Phase Shift Data ◽  
Seismic Images

Structural interpretation of seismic images can be highly subjective, especially in complex geologic settings. A single seismic image will often support multiple geologically valid interpretations. However, it is usually difficult to determine which of those interpretations are more likely than others. We have referred to this problem as structural model appraisal. We have developed the use of misfit functions to rank and appraise multiple interpretations of a given seismic image. Given a set of possible interpretations, we compute synthetic data for each structural interpretation, and then we compare these synthetic data against observed seismic data; this allows us to assign a data-misfit value to each structural interpretation. Our aim is to find data-misfit functions that enable a ranking of interpretations. To do so, we formalize the problem of appraising structural interpretations using seismic data and we derive a set of conditions to be satisfied by the data-misfit function for a successful appraisal. We investigate vertical seismic profiling (VSP) and surface seismic configurations. An application of the proposed method to a realistic synthetic model shows promising results for appraising structural interpretations using VSP data, provided that the target region is well-illuminated. However, we find appraising structural interpretations using surface seismic data to be more challenging, mainly due to the difficulty of computing phase-shift data misfits.

Relative time seislet transform

Geophysics ◽  
2020 ◽  
Vol 85 (2) ◽  
pp. V223-V232 ◽  
Author(s):  
Zhicheng Geng ◽  
Xinming Wu ◽  
Sergey Fomel ◽  
Yangkang Chen
Keyword(s):  
Seismic Data ◽  
Computational Cost ◽  
Lifting Scheme ◽  
Real Data ◽  
Data Sets ◽  
Relative Time ◽  
New Approach ◽  
New Formulation ◽  
Wavelet Lifting ◽  
Seismic Images

The seislet transform uses the wavelet-lifting scheme and local slopes to analyze the seismic data. In its definition, the designing of prediction operators specifically for seismic images and data is an important issue. We have developed a new formulation of the seislet transform based on the relative time (RT) attribute. This method uses the RT volume to construct multiscale prediction operators. With the new prediction operators, the seislet transform gets accelerated because distant traces get predicted directly. We apply our method to synthetic and real data to demonstrate that the new approach reduces computational cost and obtains excellent sparse representation on test data sets.

Detecting faults and channels while enhancing seismic structural and stratigraphic features

2019 ◽  
Vol 7 (1) ◽  
pp. T155-T166 ◽  
Author(s):  
Xinming Wu ◽  
Zhenwei Guo
Keyword(s):  
Iterative Scheme ◽  
3D Seismic ◽  
Linear Features ◽  
Smoothing Methods ◽  
Seismic Image ◽  
Diffusion Scheme ◽  
Seismic Reflections ◽  
2D And 3D ◽  
Seismic Images

A 3D seismic image contains structural and stratigraphic features such as reflections, faults, and channels. When smoothing such an image, we want to enhance all of these features so that they are easier to interpret. Most smoothing methods aim to enhance reflections but may blur faults and channels in the image. A few methods smooth seismic reflections while preserving faults and channel boundaries. However, it has not well-discussed to smooth simultaneously along the seismic reflections and channels, which are linear features apparent within dipping reflections. In addition, to interpret faults and channels, extra steps are required to compute attributes or mappings of faults and channels from a seismic image. Such fault and channel attributes are often sensitive to noise because they are typically computed as discontinuities of seismic reflections. In this paper, we have developed methods to simultaneously enhance seismic reflections, faults, and channels while obtaining mappings of the faults and channels. In these methods, we first estimate the orientations of the reflections, faults, and channels directly in a seismic image. We then use the estimated orientations to control the smoothing directions in an efficient iterative diffusion scheme to smooth a seismic image along the reflections and channels. In this iterative scheme, we also efficiently compute mappings of faults and channels, which are used to control smoothing extents in the diffusion to stop smoothing across them. This diffusion scheme iteratively smooths a seismic image along reflections and channels while updating the mappings of faults and channels. By doing this, we will finally obtain an enhanced seismic image (with enhanced reflections and channels and sharpened faults) and cleaned mappings of faults and channels (discontinuities related to noise are cleaned up). We have examined the methods using 2D and 3D real seismic images.

Extensive, Gas-charged Quaternary Sand Accumulations of the Northern North Sea and North Sea Fan

2020 ◽  
Author(s):  
Benjamin Bellwald ◽  
Sverre Planke ◽  
Sunil Vadakkepuliyambatta ◽  
Stefan Buenz ◽  
Christine Batchelor ◽  
...  
Keyword(s):  
North Sea ◽  
Seismic Data ◽  
Data Sets ◽  
3D Seismic ◽  
Fine Grained ◽  
The North ◽  
Northern North Sea ◽  
Well Data ◽  
Sea Fan ◽  
3D Seismic Data

<p>Sediments deposited by marine-based ice sheets are dominantly fine-grained glacial muds, which are commonly known for their sealing properties for migrating fluids. However, the Peon and Aviat hydrocarbon discoveries in the North Sea show that coarse-grained glacial sands can occur over large areas in formerly glaciated continental shelves. In this study, we use conventional and high-resolution 2D and 3D seismic data combined with well information to present new models for large-scale fluid accumulations within the shallow subsurface of the Norwegian Continental Shelf. The data include 48,000 km<sup>2</sup> of high-quality 3D seismic data and 150 km<sup>2</sup> of high-resolution P-Cable 3D seismic data, with a vertical resolution of 2 m and a horizontal resolution of 6 to 10 m in these data sets. We conducted horizon picking, gridding and attribute extractions as well as seismic geomorphological interpretation, and integrated the results obtained from the seismic interpretation with existing well data.</p><p>The thicknesses of the Quaternary deposits vary from hundreds of meters of subglacial till in the Northern North Sea to several kilometers of glacigenic sediments in the North Sea Fan. Gas-charged, sandy accumulations are characterized by phase-reserved reflections with anomalously high amplitudes in the seismic data as well as density and velocity decreases in the well data. Extensive (>10 km<sup>2</sup>) Quaternary sand accumulations within this package include (i) glacial sands in an ice-marginal outwash fan, sealed by stiff glacial tills deposited by repeated glaciations (the Peon discovery in the Northern North Sea), (ii) sandy channel-levee systems sealed by fine-grained mud within sequences of glacigenic debris flows, formed during shelf-edge glaciations, (iii) fine-grained glacimarine sands of contouritic origin sealed by gas hydrates, and (iv) remobilized oozes above large evacuation craters and sealed by megaslides and glacial muds. The development of the Fennoscandian Ice Sheet resulted in a rich variety of depositional environments with frequently changing types and patterns of glacial sedimentation. Extensive new 3D seismic data sets are crucial to correctly interpret glacial processes and to analyze the grain sizes of the related deposits. Furthermore, these data sets allow the identification of localized extensive fluid accumulations within the Quaternary succession and distinguish stratigraphic levels favorable for fluid accumulations from layers acting as fluid barriers.</p>

Automatically interpreting all faults, unconformities, and horizons from 3D seismic images

2016 ◽  
Vol 4 (2) ◽  
pp. T227-T237 ◽  
Author(s):  
Xinming Wu ◽  
Dave Hale
Keyword(s):  
Image Processing ◽  
Partial Differential Equations ◽  
Differential Equations ◽  
Array Processing ◽  
3D Seismic ◽  
Partial Differential ◽  
Seismic Image ◽  
Processing Procedure ◽  
Seismic Images

Extracting fault, unconformity, and horizon surfaces from a seismic image is useful for interpretation of geologic structures and stratigraphic features. Although others automate the extraction of each type of these surfaces to some extent, it is difficult to automatically interpret a seismic image with all three types of surfaces because they could intersect with each other. For example, horizons can be especially difficult to extract from a seismic image complicated by faults and unconformities because a horizon surface can be dislocated at faults and terminated at unconformities. We have proposed a processing procedure to automatically extract all the faults, unconformities, and horizon surfaces from a 3D seismic image. In our processing, we first extracted fault surfaces, estimated fault slips, and undid the faulting in the seismic image. Then, we extracted unconformities from the unfaulted image with continuous reflectors across faults. Finally, we used the unconformities as constraints for image flattening and horizon extraction. Most of the processing was image processing or array processing and was achieved by efficiently solving partial differential equations. We used a 3D real example with faults and unconformities to demonstrate the entire image processing.

Horizon extraction using ordered clustering on a directed and colored graph

2020 ◽  
Vol 8 (1) ◽  
pp. T1-T11
Author(s):  
Zhining Liu ◽  
Chengyun Song ◽  
Kunhong Li ◽  
Bin She ◽  
Xingmiao Yao ◽  
...  
Keyword(s):  
Seismic Data ◽  
Spatial Information ◽  
Spatial Distributions ◽  
Global Level ◽  
Clustering Method ◽  
Colored Graph ◽  
Seismic Image ◽  
Level Information ◽  
Novel Method ◽  
Seismic Images

Extracting horizons from a seismic image has been playing an important role in seismic interpretation. However, how to fully use global-level information contained in the seismic images such as the order of horizon sequences is not well-studied in existing works. To address this issue, we have developed a novel method based on a directed and colored graph, which encodes effective context information for horizon extraction. Following the commonly used framework, which generates horizon patches and then groups them into horizons, we first build a directed and colored graph by representing horizon patches as vertices. In addition, edges in the graph encode the relative spatial positions of horizon patches. This graph explicitly captures the geologic context, which guides the grouping of the horizon patches. Then, we conduct premerging to group horizon patches through matching some predefined subgraph patterns that are designed to capture some special spatial distributions of horizon patches. Finally, we have developed an ordered clustering method to group the rest of the horizon patches into horizons based on the pairwise similarities of horizon patches while preserving geologic reasonability. Experiments on real seismic data indicate that our method can outperform the autotracking approach solely based on the similarity of local waveforms and can correctly pick the horizons even across the fault without any crossing, which demonstrates the effectiveness of exploring the spatial information, i.e., the order of horizon sequences and special spatial distribution of horizon patches.

scholarly journals Time-lapse difference static correction using prestack crosscorrelations: 4D seismic image enhancement case from Ketzin

Geophysics ◽  
2014 ◽  
Vol 79 (6) ◽  
pp. B243-B252 ◽  
Author(s):  
Peter Bergmann ◽  
Artem Kashubin ◽  
Monika Ivandic ◽  
Stefan Lüth ◽  
Christopher Juhlin
Keyword(s):  
Seismic Data ◽  
Time Lapse ◽  
Data Sets ◽  
Storage Site ◽  
Data Set ◽  
Near Surface ◽  
Static Correction ◽  
Seismic Image ◽  
Static Corrections ◽  
4D Seismic

A method for static correction of time-lapse differences in reflection arrival times of time-lapse prestack seismic data is presented. These arrival-time differences are typically caused by changes in the near-surface velocities between the acquisitions and had a detrimental impact on time-lapse seismic imaging. Trace-to-trace time shifts of the data sets from different vintages are determined by crosscorrelations. The time shifts are decomposed in a surface-consistent manner, which yields static corrections that tie the repeat data to the baseline data. Hence, this approach implies that new refraction static corrections for the repeat data sets are unnecessary. The approach is demonstrated on a 4D seismic data set from the Ketzin [Formula: see text] pilot storage site, Germany, and is compared with the result of an initial processing that was based on separate refraction static corrections. It is shown that the time-lapse difference static correction approach reduces 4D noise more effectively than separate refraction static corrections and is significantly less labor intensive.

Sign in / Sign up

Export Citation Format

Share Document