scholarly journals Automatic inspection and analysis of digital waveform images by means of convolutional neural networks

2021 ◽  
Author(s):  
Alessandro Pignatelli ◽  
Francesca D’Ajello Caracciolo ◽  
Rodolfo Console
Keyword(s):  
Seismic Data ◽  
Technological Development ◽  
Automatic Inspection ◽  
Earthquake Epicenter ◽  
Major Task ◽  
Convolutional Networks ◽  
Seismic Waveform ◽  
Observation Systems ◽  
Recording Station ◽  
Wave Image

AbstractAnalyzing seismic data to get information about earthquakes has always been a major task for seismologists and, more in general, for geophysicists. Recently, thanks to the technological development of observation systems, more and more data are available to perform such tasks. However, this data “grow up” makes “human possibility” of data processing more complex in terms of required efforts and time demanding. That is why new technological approaches such as artificial intelligence are becoming very popular and more and more exploited. In this paper, we explore the possibility of interpreting seismic waveform segments by means of pre-trained deep learning. More specifically, we apply convolutional networks to seismological waveforms recorded at local or regional distances without any pre-elaboration or filtering. We show that such an approach can be very successful in determining if an earthquake is “included” in the seismic wave image and in estimating the distance between the earthquake epicenter and the recording station.

scholarly journals Batch seismic inversion using the iterative ensemble Kalman smoother

2021 ◽  
Author(s):  
Michael Gineste ◽  
Jo Eidsvik
Keyword(s):  
Seismic Data ◽  
Time Windows ◽  
Seismic Inversion ◽  
Efficient Estimation ◽  
Solution Strategy ◽  
Adaptive Procedure ◽  
Waveform Data ◽  
Kalman Smoother ◽  
Seismic Waveform ◽  
Single Batch

AbstractAn ensemble-based method for seismic inversion to estimate elastic attributes is considered, namely the iterative ensemble Kalman smoother. The main focus of this work is the challenge associated with ensemble-based inversion of seismic waveform data. The amount of seismic data is large and, depending on ensemble size, it cannot be processed in a single batch. Instead a solution strategy of partitioning the data recordings in time windows and processing these sequentially is suggested. This work demonstrates how this partitioning can be done adaptively, with a focus on reliable and efficient estimation. The adaptivity relies on an analysis of the update direction used in the iterative procedure, and an interpretation of contributions from prior and likelihood to this update. The idea is that these must balance; if the prior dominates, the estimation process is inefficient while the estimation is likely to overfit and diverge if data dominates. Two approaches to meet this balance are formulated and evaluated. One is based on an interpretation of eigenvalue distributions and how this enters and affects weighting of prior and likelihood contributions. The other is based on balancing the norm magnitude of prior and likelihood vector components in the update. Only the latter is found to sufficiently regularize the data window. Although no guarantees for avoiding ensemble divergence are provided in the paper, the results of the adaptive procedure indicate that robust estimation performance can be achieved for ensemble-based inversion of seismic waveform data.

Wavelet transform with generalized beta wavelets for seismic time-frequency analysis

Geophysics ◽  
2017 ◽  
Vol 82 (4) ◽  
pp. O47-O56 ◽  
Author(s):  
Zhiguo Wang ◽  
Bing Zhang ◽  
Jinghuai Gao ◽  
Qingzhen Wang ◽  
Qing Huo Liu
Keyword(s):  
Wavelet Transform ◽  
Frequency Analysis ◽  
Seismic Data ◽  
Significant Information ◽  
Trade Off ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Reflection Seismic ◽  
Seismic Waveform ◽  
Frequency Representation

Using the continuous wavelet transform (CWT), the time-frequency analysis of reflection seismic data can provide significant information to delineate subsurface reservoirs. However, CWT is limited by the Heisenberg uncertainty principle, with a trade-off between time and frequency localizations. Meanwhile, the mother wavelet should be adapted to the real seismic waveform. Therefore, for a reflection seismic signal, we have developed a progressive wavelet family that is referred to as generalized beta wavelets (GBWs). By varying two parameters controlling the wavelet shapes, the time-frequency representation of GBWs can be given sufficient flexibility while remaining exactly analytic. To achieve an adaptive trade-off between time-frequency localizations, an optimization workflow is designed to estimate suitable parameters of GBWs in the time-frequency analysis of seismic data. For noise-free and noisy synthetic signals from a depositional cycle model, the results of spectral component using CWT with GBWs display its flexibility and robustness in the adaptive time-frequency representation. Finally, we have applied CWT with GBWs on 3D seismic data to show its potential to discriminate stacked fluvial channels in the vertical sections and to delineate more distinct fluvial channels in the horizontal slices. CWT with GBWs provides a potential technique to improve the resolution of exploration seismic interpretation.

scholarly journals Technique for the imaging crystalline basement according to the DSS data

2021 ◽  
Vol 43 (5) ◽  
pp. 127-149
Author(s):  
O. O. Verpakhovska
Keyword(s):  
Finite Difference ◽  
Seismic Data ◽  
Deep Structure ◽  
Crystalline Basement ◽  
National Academy Of Sciences ◽  
Reflected Waves ◽  
Advantages And Disadvantages ◽  
Observation Systems ◽  
Layer Medium ◽  
Refracted Waves

The method of deep seismic sounding (DSS), the observation systems in which are characterized by an irregular arrangement of both sources and receivers along the profile, a significant step between receivers, as well as maximum source-receiver distances exceeding several hundred kilometers, makes it possible to obtain an image of the crystalline basement using seismic migration fields of reflected/refracted waves. The main part of the existing migration methods, the use of which makes it possible to form an image of the deep structure of the study area in the dynamic characteristics of the recorded wave field, is focused on processing seismic data obtained by the method of reflected waves with multiple overlap observation systems (MOV—CDP). And, as a rule, these migration methods are designed for a smooth change in speed with depth. At the same time, at the boundary of the crystalline basement, the speed changes very sharply, which must be taken into account when processing data using migration. The proposed method for constructing an image of the crystalline basement is based on the use of finite-difference migration of the field of reflected/refracted waves, which was developed at the Institute of Geophysics named after S. I. Subbotin National Academy of Sciences of Ukraine. This migration method is designed to isolate supercritically reflected and refracted waves recorded from the basement in the far zone of the source and takes into account the full trajectory of waves passing through a two-layer medium, at the boundary of which there is a significant jump in velocity. Thus, the migration of the field of reflected/refracted waves makes it possible to obtain a correct image of the structure of the refractive layer of the crystalline basement. The article describes in detail the algorithm of the technique for constructing an image of the crystalline basement using finite-difference migration of the field of reflected/refracted waves and its difference from similar methods of migration. The advantages and disadvantages of the proposed method are shown when solving problems of regional seismic research. Explained and illustrated the features of constructing the image of violations on the border of the foundation. The effectiveness of the technique is demonstrated on a model example and real seismic data observed by the DSS method on the territory of Ukraine.

THE APPLICATION OF 3D SEISMIC INTERPRETATION TECHNIQUES FOR OPTIMISING WELL PLACEMENT: FORTESCUE FIELD RE DEVELOPMENT, GIPPSLAND BASIN

1997 ◽  
Vol 37 (1) ◽  
pp. 31
Author(s):  
P.J. Ryan ◽  
T.E. Vinson
Keyword(s):  
High Precision ◽  
Seismic Data ◽  
Development Program ◽  
Seismic Interpretation ◽  
3D Seismic ◽  
Well Placement ◽  
Seismic Waveform ◽  
Attribute Analysis ◽  
Definition Of ◽  
Gippsland Basin

In order to achieve successful drilling results on mature fields, geophysical analysis has become increasingly focussed on the application of high precision 3D seismic interpretation and analysis techniques. These techniques were critical to the success of the re-development program recently completed on the Fortescue Field* Gippsland Basin. Fortescue, initially developed in 1983, contains an estimated oil reserve of 300 million barrels. The field is currently over 80 percent depleted. To offset declining production and develop remaining reserves, an 18 well additional drilling program together with upgrades to platform topsides and production facilities was conducted on the field from October 1994 to October 1996.Many of the proposed additional drilling opportunities relied on oil being trapped structurally updip from existing completions. Given the size (approx. 1 MSTB) and subtle, low relief nature of the targets being pursued, the precision of conventional 3D seismic interpretation techniques was inadequate to optimise the location of wells. This necessitated the development of a series of specific tools that could provide high resolution definition of both the trap and lithology as well as optimising well placement.These high precision interpretation techniques include: reservoir subcrop edge prediction through qualitative calibration of geological models to seismic data: the assessment of overburden velocity distortions of the seismic time field by utilising isochron mapping and interval attribute analysis; and prediction of trap geometries and lateral stratigraphic variations by the application of seismic waveform attributes.The application of these advanced 3D seismic interpretation techniques and their integration with related geoscience and engineering technologies resulted in the completion of a successful 18 well re-development program for the Fortescue field.

Data-driven Prestack Waveform Inversion Using Genetic Algorithm- Methodology and Examples

2021 ◽  
pp. 1-97
Author(s):  
Lingxiao Jia ◽  
Subhashis Mallick ◽  
Cheng Wang
Keyword(s):  
Genetic Algorithm ◽  
Seismic Data ◽  
Waveform Inversion ◽  
Seismic Inversion ◽  
P Wave ◽  
Data Driven ◽  
Initial Model ◽  
Reservoir Properties ◽  
Well Control ◽  
Seismic Waveform

The choice of an initial model for seismic waveform inversion is important. In matured exploration areas with adequate well control, we can generate a suitable initial model using well information. However, in new areas where well control is sparse or unavailable, such an initial model is compromised and/or biased by the regions with more well controls. Even in matured exploration areas, if we use time-lapse seismic data to predict dynamic reservoir properties, an initial model, that we obtain from the existing preproduction wells could be incorrect. In this work, we outline a new methodology and workflow for a nonlinear prestack isotropic elastic waveform inversion. We call this method a data driven inversion, meaning that we derive the initial model entirely from the seismic data without using any well information. By assuming a locally horizonal stratification for every common midpoint and starting from the interval P-wave velocity, estimated entirely from seismic data, our method generates pseudo wells by running a two-pass one-dimensional isotropic elastic prestack waveform inversion that uses the reflectivity method for forward modeling and genetic algorithm for optimization. We then use the estimated pseudo wells to build the initial model for seismic inversion. By applying this methodology to real seismic data from two different geological settings, we demonstrate the usefulness of our method. We believe that our new method is potentially applicable for subsurface characterization in areas where well information is sparse or unavailable. Additional research is however necessary to improve the compute-efficiency of the methodology.

Prestack waveform inversion of three-dimensional seismic data — An example from the Rock Springs Uplift, Wyoming, USA

Geophysics ◽  
2017 ◽  
Vol 82 (1) ◽  
pp. B1-B12 ◽  
Author(s):  
Josiane Pafeng ◽  
Subhashis Mallick ◽  
Hema Sharma
Keyword(s):  
Seismic Data ◽  
Reservoir Characterization ◽  
Waveform Inversion ◽  
Three Dimensional ◽  
Seismic Inversion ◽  
Amplitude Variation ◽  
Amplitude Variation With Offset ◽  
Seismic Waveform ◽  
Rock Springs Uplift ◽  
Rock Springs

Applying seismic inversion to estimate subsurface elastic earth properties for reservoir characterization is a challenge in exploration seismology. In recent years, waveform-based seismic inversions have gained popularity, but due to high computational costs, their applications are limited, and amplitude-variation-with-offset/angle inversion is still the current state-of-the-art. We have developed a genetic-algorithm-based prestack seismic waveform inversion methodology. By parallelizing at multiple levels and assuming a locally 1D structure such that forward computation of wave equation synthetics is computationally efficient, this method is capable of inverting 3D prestack seismic data on parallel computers. Applying this inversion to a real prestack seismic data volume from the Rock Springs Uplift (RSU) located in Wyoming, USA, we determined that our method is capable of inverting the data in a reasonable runtime and producing much higher quality results than amplitude-variation-with-offset/angle inversion. Because the primary purpose for seismic data acquisition at the RSU was to characterize the subsurface for potential targets for carbon dioxide sequestration, we also identified and analyzed some potential primary and secondary storage formations and their associated sealing lithologies from our inversion results.

scholarly journals Convolutional Neural Network to Detect Deep Low-Frequency Tremors from Seismic Waveform Images

2021 ◽  
pp. 31-43
Author(s):  
Ryosuke Kaneko ◽  
Hiromichi Nagao ◽  
Shin-ichi Ito ◽  
Kazushige Obara ◽  
Hiroshi Tsuruoka
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Seismic Data ◽  
Low Frequency ◽  
Seismic Waveforms ◽  
Seismic Waveform ◽  
Numerous Paper ◽  
Large Earthquakes ◽  
Activation Mapping

AbstractThe installation of dense seismometer arrays in Japan approximately 20 years ago has led to the discovery of deep low-frequency tremors, which are oscillations clearly different from ordinary earthquakes. As such tremors may be related to large earthquakes, it is an important issue in seismology to investigate tremors that occurred before establishing dense seismometer arrays. We use deep learning aiming to detect evidence of tremors from past seismic data of more than 50 years ago, when seismic waveforms were printed on paper. First, we construct a convolutional neural network (CNN) based on the ResNet architecture to extract tremors from seismic waveform images. Experiments applying the CNN to synthetic images generated according to seismograph paper records show that the trained model can correctly determine the presence of tremors in the seismic waveforms. In addition, the gradient-weighted class activation mapping clearly indicates the tremor location on each image. Thus, the proposed CNN has a strong potential for detecting tremors on numerous paper records, which can enable to deepen the understanding of the relations between tremors and earthquakes.

Seismic Waveform Data from Greece and Cyprus: Integration, Archival, and Open Access

2021 ◽  
Author(s):  
Christos P. Evangelidis ◽  
Nikolaos Triantafyllis ◽  
Michalis Samios ◽  
Kostas Boukouras ◽  
Kyriakos Kontakos ◽  
...  
Keyword(s):  
Seismic Data ◽  
Data Center ◽  
Ambient Noise ◽  
Strong Motion ◽  
Data Availability ◽  
Data Archive ◽  
Waveform Data ◽  
The Balkans ◽  
Seismic Waveform ◽  
Data Archives

Abstract The National Observatory of Athens data center for the European Integrated Data Archive (EIDA@NOA) is the national and regional node that supports International Federation of Digital Seismograph Networks and related webservices for seismic waveform data coming from the southeastern Mediterranean and the Balkans. At present, it serves data from eight permanent broadband and strong-motion networks from Greece and Cyprus, individual stations from the Balkans, temporary networks and aftershock deployments, and earthquake engineering experimental facilities. EIDA@NOA provides open and unlimited access from redundant node end points, intended mainly for research purposes (see Data and Resources). Analysis and quality control of the complete seismic data archive is performed initially by calculating waveform metrics and data availability. Seismic ambient noise metrics are estimated based on power spectral densities, and an assessment of each station’s statistical mode is achieved within each network and across networks. Moreover, the minimum ambient noise level expected for strong-motion installations is defined. Sensor orientation is estimated using surface-wave polarization methods to detect stations with misalignment on particular epochs. A single data center that hosts the complete seismic data archives with their respective metadata from networks covering similar geographical areas allows coordination between network operators and facilitates the adhesion to widely used best practices regarding station installation, data curation, and metadata definition. The overall achievement is harmonization among all contributing networks and a wider usage of all data archives, ultimately strengthening seismological research efforts in the region.

Sign in / Sign up

Export Citation Format

Share Document