scholarly journals Neural networks for geophysicists and their application to seismic data interpretation

2019 ◽  
Vol 38 (7) ◽  
pp. 534-540 ◽  
Author(s):  
Bas Peters ◽  
Eldad Haber ◽  
Justin Granek
Keyword(s):  
Neural Networks ◽  
Seismic Data ◽  
Data Interpretation ◽  
Forward Modeling ◽  
The North ◽  
Automatic Interpretation ◽  
The North Sea ◽  
Similarities And Differences ◽  
And Inversion ◽  
Seismic Images

There has been a surge of interest in neural networks for the interpretation of seismic images over the last few years. Network-based learning methods can provide fast and accurate automatic interpretation, provided that there are many training labels. We provide an introduction to the field for geophysicists who are familiar with the framework of forward modeling and inversion. We explain the similarities and differences between deep networks and other geophysical inverse problems and show their utility in solving problems such as lithology interpolation between wells, horizon tracking, and segmentation of seismic images. The benefits of our approach are demonstrated on field data from the Sea of Ireland and the North Sea.

Timing of magmatism, foreland basin development, metamorphism and inversion in the Anglo-Brabant fold belt

1997 ◽  
Vol 134 (5) ◽  
pp. 607-616 ◽  
Author(s):  
G. VAN GROOTEL ◽  
J. VERNIERS ◽  
B. GEERKENS ◽  
D. LADURON ◽  
M. VERHAEREN ◽  
...  
Keyword(s):  
Subduction Zones ◽  
Foreland Basin ◽  
Fold Belt ◽  
East Anglia ◽  
Basin Inversion ◽  
Tectonic Model ◽  
The North ◽  
Basin Development ◽  
The North Sea ◽  
And Inversion

New data implying crustal activation of Eastern Avalonia along the Anglo-Brabant fold belt are presented. Late Ordovician subduction-related magmatism in East Anglia and the Brabant Massif, coupled with accelerated subsidence in the Anglia Basin and in the Brabant Massif during Silurian time, indicate a foreland basin development. Final collision resulted in folding, cleavage development and thrusting during the mid-Lochkovian to mid-Eifelian. In the southeast of the Anglo-Brabant fold belt, Acadian deformation produced basin inversion and the regional antiformal structure of the Brabant Massif. The uplift, inferred from the sedimentology, petrography and reworked palynomorphs in the Lower Devonian of the Dinant Synclinorium is confirmed by illite crystallinity studies. The tectonic model discussed implies the presence of two subduction zones in the eastern part of Eastern Avalonia, one along the Anglo-Brabant fold belt and another under the North Sea in the prolongation of the North German–Polish Caledonides.

Fault Detection by Using Instance Segmentation

2021 ◽  
Author(s):  
Donglin Zhu ◽  
Lei Li ◽  
Rui Guo ◽  
Shifan Zhan
Keyword(s):  
Fault Detection ◽  
Seismic Data ◽  
Semantic Segmentation ◽  
Data Interpretation ◽  
Machine Learning Methods ◽  
Segmentation Algorithms ◽  
Direct Recognition ◽  
First Time ◽  
Seismic Images ◽  
Instance Segmentation

Abstract Fault detection is an important, but time-consuming task in seismic data interpretation. Traditionally, seismic attributes, such as coherency (Marfurt et al., 1998) and curvature (Al-Dossary et al., 2006) are used to detect faults. Recently, machine learning methods, such as convolution neural networks (CNNs) are used to detect faults, by applying various semantic segmentation algorithms to the seismic data (Wu et al., 2019). The most used algorithm is U-Net (Ronneberger et al., 2015), which can accurately and efficiently provide probability maps of faults. However, probabilities of faults generated by semantic segmentation algorithms are not sufficient for direct recognition of fault types and reconstruction of fault surfaces. To address this problem, we propose, for the first time, a workflow to use instance segmentation algorithm to detect different fault lines. Specifically, a modified CNN (LaneNet; Neven et al., 2018) is trained using automatically generated synthetic seismic images and corresponding labels. We then test the trained CNN using both synthetic and field collected seismic data. Results indicate that the proposed workflow is accurate and effective at detecting faults.

Case Study of Broadband Multimeasurement Streamer and Multilevel Source Seismic Data from the North Sea

2015 ◽  
Author(s):  
A.V. Zarkhidze ◽  
Y. Abbas ◽  
P.E. Dhelie ◽  
V. Danielsen ◽  
J.E. Lie
Keyword(s):  
North Sea ◽  
Seismic Data ◽  
The North ◽  
The North Sea

Delineation of tunnel valleys across the North Sea coastline, Denmark based on reflection seismic data, boreholes, TEM and Schlumberger soundings

2016 ◽  
Vol 2016 (1) ◽  
pp. 1-10
Author(s):  
Theis Raaschou Andersen ◽  
Flemming Jorgensen ◽  
Steen Christensen
Keyword(s):  
North Sea ◽  
Seismic Data ◽  
Reflection Seismic ◽  
The North ◽  
The North Sea

Imaging the sea surface using a dual-sensor towed streamer

Geophysics ◽  
2010 ◽  
Vol 75 (6) ◽  
pp. V111-V118 ◽  
Author(s):  
Okwudili Orji ◽  
Walter Söllner ◽  
Leiv Jacob Gelius
Keyword(s):  
Seismic Data ◽  
Time Window ◽  
Finite Difference Methods ◽  
Surface Profile ◽  
Sea Surface ◽  
Data Sets ◽  
The North ◽  
Dual Sensor ◽  
The North Sea ◽  
Time Invariant

Sea-surface profile and reflection coefficient estimates are vital input parameters to various seismic data processing applications. The common assumption of a flat sea surface when processing seismic data can lead to misinterpretations and mislocations of events. A new method of imaging the sea surface from decomposed wavefields has been developed. Wavefield separation is applied to the data acquired by a towed dual-sensor streamer containing collocated pressure and vertical particle velocity sensors to obtain upgoing and downgoing wavefields of the related sensors. Time-gated upgoing and downgoing wavefields corresponding to a given sensor are then extrapolated to the sea surface where an imaging condition is applied so that the time-invariant shape of the sea surface can be recovered. By sliding the data time-window, the temporal changes of the sea surface can be correspondingly estimated. Ray tracing and finite-difference methods were used to generate different controlled data sets used in this feasibility study to demonstrate the imaging principle and to test the image accuracy. The method was also tested on a first field data example of a marginal weather line from the North Sea.

Quaternary evolution of the northern North Sea

2020 ◽  
Author(s):  
Christine Batchelor ◽  
Dag Ottesen ◽  
Benjamin Bellwald ◽  
Sverre Planke ◽  
Helge Løseth ◽  
...  
Keyword(s):  
North Sea ◽  
Seismic Data ◽  
3D Seismic ◽  
Quaternary Sediments ◽  
The North ◽  
The North Sea ◽  
Data Coverage ◽  
Northern North Sea ◽  
2D And 3D ◽  
3D Seismic Data

<p>The North Sea has arguably the most extensive geophysical data coverage of any glacier-influenced sedimentary regime on Earth, enabling detailed investigation of the thick (up to 1 km) sequence of Quaternary sediments that is preserved within the North Sea Basin. At the start of the Quaternary, the bathymetry of the northern North Sea was dominated by a deep depression that provided accommodation for sediment input from the Norwegian mainland and the East Shetland Platform. Here we use an extensive database of 2D and 3D seismic data to investigate the geological development of the northern North Sea through the Quaternary.</p><p>Three main sedimentary processes were dominant within the northern North Sea during the early Quaternary: 1) the delivery and associated basinward transfer of glacier-derived sediments from an ice mass centred over mainland Norway; 2) the delivery of fluvio-deltaic sediments from the East Shetland Platform; and 3) contourite deposition and the reworking of sediments by contour currents. The infilling of the North Sea Basin during the early Quaternary increased the width and reduced the water depth of the continental shelf, facilitating the initiation of the Norwegian Channel Ice Stream.</p>

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.

High-resolution reservoir characterization by an acoustic impedance inversion of a Tertiary deltaic clinoform system in the North Sea

Geophysics ◽  
2010 ◽  
Vol 75 (6) ◽  
pp. O57-O67 ◽  
Author(s):  
Daria Tetyukhina ◽  
Lucas J. van Vliet ◽  
Stefan M. Luthi ◽  
Kees Wapenaar
Keyword(s):  
North Sea ◽  
Seismic Data ◽  
Reservoir Characterization ◽  
Structural Information ◽  
Sampling Rate ◽  
Seismic Inversion ◽  
Acoustic Properties ◽  
The North ◽  
The North Sea ◽  
Well Data

Fluvio-deltaic sedimentary systems are of great interest for explorationists because they can form prolific hydrocarbon plays. However, they are also among the most complex and heterogeneous ones encountered in the subsurface, and potential reservoir units are often close to or below seismic resolution. For seismic inversion, it is therefore important to integrate the seismic data with higher resolution constraints obtained from well logs, whereby not only the acoustic properties are used but also the detailed layering characteristics. We have applied two inversion approaches for poststack, time-migrated seismic data to a clinoform sequence in the North Sea. Both methods are recursive trace-based techniques that use well data as a priori constraints but differ in the way they incorporate structural information. One method uses a discrete layer model from the well that is propagated laterally along the clinoform layers, which are modeled as sigmoids. The second method uses a constant sampling rate from the well data and uses horizontal and vertical regularization parameters for lateral propagation. The first method has a low level of parameterization embedded in a geologic framework and is computationally fast. The second method has a much higher degree of parameterization but is flexible enough to detect deviations in the geologic settings of the reservoir; however, there is no explicit geologic significance and the method is computationally much less efficient. Forward seismic modeling of the two inversion results indicates a good match of both methods with the actual seismic data.

Sign in / Sign up

Export Citation Format

Share Document