Joint inversion of seismic data for acoustic impedance

Geophysics ◽  
2004 ◽  
Vol 69 (4) ◽  
pp. 994-1004 ◽  
Author(s):  
Li‐Yun Fu
Keyword(s):  
Neural Network ◽  
Seismic Data ◽  
Acoustic Impedance ◽  
Joint Inversion ◽  
Signal Reconstruction ◽  
Optimal Estimation ◽  
Data Sets ◽  
Seismic Wavelet ◽  
Model Based ◽  
Band Limited

I propose a joint inversion scheme to integrate seismic data, well data, and geological knowledge for acoustic impedance estimation. I examine the problem of recovering acoustic impedance from band‐limited seismic data. Optimal estimation of impedance can be achieved by combined applications of model‐based and deconvolution‐based methods. I incorporate the Robinson seismic convolutional model (RSCM) into the Caianiello neural network for network mapping. The Caianiello neural network provides an efficient approach to decompose the seismic wavelet and its inverse. The joint inversion consists of four steps: (1) multistage seismic inverse wavelets (MSIW) extraction at the wells, (2) the deconvolution with MSIW for initial impedance estimation, (3) multistage seismic wavelets (MSW) extraction at the wells, and (4) the model‐based reconstruction of impedance with MSW for improving the initial impedance model. The Caianiello neural network offers two algorithms for the four‐step process: neural wavelet estimation and input signal reconstruction. The frequency‐domain implementation of the algorithms enables control of the inversion on different frequency scales and facilitates an understanding of reservoir behavior on different resolution scales. The test results show that, with well control, the joint inversion can significantly improve the spatial description of reservoirs in data sets involving complex continental deposits.

Accurate poststack acoustic-impedance inversion by well-log calibration

Geophysics ◽  
2009 ◽  
Vol 74 (5) ◽  
pp. R59-R67 ◽  
Author(s):  
Igor B. Morozov ◽  
Jinfeng Ma
Keyword(s):  
Seismic Data ◽  
Acoustic Impedance ◽  
Joint Inversion ◽  
Low Frequency ◽  
Real Data ◽  
Data Sets ◽  
Frequency Model ◽  
Physical Constraints ◽  
Impedance Inversion ◽  
Reliable Solution

The seismic-impedance inversion problem is underconstrained inherently and does not allow the use of rigorous joint inversion. In the absence of a true inverse, a reliable solution free from subjective parameters can be obtained by defining a set of physical constraints that should be satisfied by the resulting images. A method for constructing synthetic logs is proposed that explicitly and accurately satisfies (1) the convolutional equation, (2) time-depth constraints of the seismic data, (3) a background low-frequency model from logs or seismic/geologic interpretation, and (4) spectral amplitudes and geostatistical information from spatially interpolated well logs. The resulting synthetic log sections or volumes are interpretable in standard ways. Unlike broadly used joint-inversion algorithms, the method contains no subjectively selected user parameters, utilizes the log data more completely, and assesses intermediate results. The procedure is simple and tolerant to noise, and it leads to higher-resolution images. Separating the seismic and subseismic frequency bands also simplifies data processing for acoustic-impedance (AI) inversion. For example, zero-phase deconvolution and true-amplitude processing of seismic data are not required and are included automatically in this method. The approach is applicable to 2D and 3D data sets and to multiple pre- and poststack seismic attributes. It has been tested on inversions for AI and true-amplitude reflectivity using 2D synthetic and real-data examples.

Colored and linear inversions to relative acoustic impedance

Geophysics ◽  
2019 ◽  
Vol 84 (2) ◽  
pp. N15-N27 ◽  
Author(s):  
Carlos A. M. Assis ◽  
Henrique B. Santos ◽  
Jörg Schleicher
Keyword(s):  
Seismic Data ◽  
Acoustic Impedance ◽  
Computational Cost ◽  
Synthetic Data ◽  
Seismic Source ◽  
Alternative Methods ◽  
Well Log ◽  
Linear Inversion ◽  
Amplitude Inversion ◽  
Band Limited

Acoustic impedance (AI) is a widely used seismic attribute in stratigraphic interpretation. Because of the frequency-band-limited nature of seismic data, seismic amplitude inversion cannot determine AI itself, but it can only provide an estimate of its variations, the relative AI (RAI). We have revisited and compared two alternative methods to transform stacked seismic data into RAI. One is colored inversion (CI), which requires well-log information, and the other is linear inversion (LI), which requires knowledge of the seismic source wavelet. We start by formulating the two approaches in a theoretically comparable manner. This allows us to conclude that both procedures are theoretically equivalent. We proceed to check whether the use of the CI results as the initial solution for LI can improve the RAI estimation. In our experiments, combining CI and LI cannot provide superior RAI results to those produced by each approach applied individually. Then, we analyze the LI performance with two distinct solvers for the associated linear system. Moreover, we investigate the sensitivity of both methods regarding the frequency content present in synthetic data. The numerical tests using the Marmousi2 model demonstrate that the CI and LI techniques can provide an RAI estimate of similar accuracy. A field-data example confirms the analysis using synthetic-data experiments. Our investigations confirm the theoretical and practical similarities of CI and LI regardless of the numerical strategy used in LI. An important result of our tests is that an increase in the low-frequency gap in the data leads to slightly deteriorated CI quality. In this case, LI required more iterations for the conjugate-gradient least-squares solver, but the final results were not much affected. Both methodologies provided interesting RAI profiles compared with well-log data, at low computational cost and with a simple parameterization.

scholarly journals Core looseness fault identification model based on Mel spectrogram-CNN

2021 ◽  
Vol 2137 (1) ◽  
pp. 012060
Author(s):  
Ping He ◽  
Yong Li ◽  
Shoulong Chen ◽  
Hoghua Xu ◽  
Lei Zhu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Convolution Neural Network ◽  
Data Sets ◽  
Data Set ◽  
Recognition Model ◽  
Model Based ◽  
Fault Recognition ◽  
Transformer Core ◽  
Identification Model

Abstract In order to realize transformer voiceprint recognition, a transformer voiceprint recognition model based on Mel spectrum convolution neural network is proposed. Firstly, the transformer core looseness fault is simulated by setting different preloads, and the sound signals under different preloads are collected; Secondly, the sound signal is converted into a spectrogram that can be trained by convolutional neural network, and then the dimension is reduced by Mel filter bank to draw Mel spectrogram, which can generate spectrogram data sets under different preloads in batch; Finally, the data set is introduced into convolutional neural network for training, and the transformer voiceprint fault recognition model is obtained. The results show that the training accuracy of the proposed Mel spectrum convolution neural network transformer identification model is 99.91%, which can well identify the core loosening faults.

scholarly journals Detection of Tectonically Deformed Coal Using Model-Based Joint Inversion of Multi-Component Seismic Data

Energies ◽  
2018 ◽  
Vol 11 (4) ◽  
pp. 829 ◽  
Author(s):  
Jun Lu ◽  
Yun Wang ◽  
Jingyi Chen
Keyword(s):  
Seismic Data ◽  
Joint Inversion ◽  
Tectonically Deformed Coal ◽  
Model Based

Time-lapse acoustic impedance variations during CO2 injection in Weyburn oilfield, Canada

Geophysics ◽  
2019 ◽  
Vol 85 (1) ◽  
pp. M1-M13 ◽  
Author(s):  
Yichuan Wang ◽  
Igor B. Morozov
Keyword(s):  
Oil Recovery ◽  
Seismic Data ◽  
Acoustic Impedance ◽  
Time Lapse ◽  
Time Shift ◽  
Co2 Injection ◽  
Inversion Method ◽  
Data Sets ◽  
Storage Site ◽  
Data Set

For seismic monitoring injected fluids during enhanced oil recovery or geologic [Formula: see text] sequestration, it is useful to measure time-lapse (TL) variations of acoustic impedance (AI). AI gives direct connections to the mechanical and fluid-related properties of the reservoir or [Formula: see text] storage site; however, evaluation of its subtle TL variations is complicated by the low-frequency and scaling uncertainties of this attribute. We have developed three enhancements of TL AI analysis to resolve these issues. First, following waveform calibration (cross-equalization) of the monitor seismic data sets to the baseline one, the reflectivity difference was evaluated from the attributes measured during the calibration. Second, a robust approach to AI inversion was applied to the baseline data set, based on calibration of the records by using the well-log data and spatially variant stacking and interval velocities derived during seismic data processing. This inversion method is straightforward and does not require subjective selections of parameterization and regularization schemes. Unlike joint or statistical inverse approaches, this method does not require prior models and produces accurate fitting of the observed reflectivity. Third, the TL AI difference is obtained directly from the baseline AI and reflectivity difference but without the uncertainty-prone subtraction of AI volumes from different seismic vintages. The above approaches are applied to TL data sets from the Weyburn [Formula: see text] sequestration project in southern Saskatchewan, Canada. High-quality baseline and TL AI-difference volumes are obtained. TL variations within the reservoir zone are observed in the calibration time-shift, reflectivity-difference, and AI-difference images, which are interpreted as being related to the [Formula: see text] injection.

Relative acoustic impedance from wavelet transform

2014 ◽  
Vol 2 (1) ◽  
pp. SA107-SA118 ◽  
Author(s):  
Marcílio Castro de Matos ◽  
Rodrigo Penna ◽  
Paulo Johann ◽  
Kurt Marfurt
Keyword(s):  
Wavelet Transform ◽  
Continuous Wavelet Transform ◽  
Seismic Data ◽  
Acoustic Impedance ◽  
Real Data ◽  
Velocity Model ◽  
Continuous Wavelet ◽  
Reconstruction Process ◽  
Seismic Wavelet ◽  
Morlet Continuous Wavelet Transform

Most deconvolution algorithms try to transform the seismic wavelet into spikes by designing inverse filters that remove an estimated seismic wavelet from seismic data. We assume that seismic trace subtle discontinuities are associated with acoustic impedance contrasts and can be characterized by wavelet transform spectral ridges, also called modulus maxima lines (WTMML), allowing us to improve seismic resolution by using the wavelet transform. Specifically, we apply the complex Morlet continuous wavelet transform (CWT) to each seismic trace and compute the WTMMLs. Then, we reconstruct the seismic trace with the inverse continuous wavelet transform from the computed WTMMLs with a broader band complex Morlet wavelet than that used in the forward CWT. Because the reconstruction process preserves amplitude and phase along different scales, or frequencies, the result looks like a deconvolution method. Considering this high-resolution seismic representation as a reflectivity approximation, we estimate the relative acoustic impedance (RAI) by filtering and trace integrating it. Conventional deconvolution algorithms assume the seismic wavelet to be stochastic, while the CWT is implicitly time varying such that it can be applied to both depth and time-domain data. Using synthetic and real seismic data, we evaluated the effectiveness of the methodology on detecting seismic events associated with acoustic impedance changes. In the real data examples, time and in-depth RAI results, show good correlation with real P-impedance band-pass data computed using more rigorous commercial inversion software packages that require well logs and low-frequency velocity model information.

scholarly journals A graph neural network fused with multi-head attention for text classification

2021 ◽  
Vol 2132 (1) ◽  
pp. 012032
Author(s):  
Bing Ai ◽  
Yibing Wang ◽  
Liang Ji ◽  
Jia Yi ◽  
Ting Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Text Classification ◽  
Data Sets ◽  
Global Information ◽  
Memory Consumption ◽  
The Past ◽  
Model Based ◽  
Improved Model

Abstract Graph neural network (GNN) has done a good job of processing intricate architecture and fusion of global messages, research has explored GNN technology for text classification. However, the model that fixed the entire corpus as a graph in the past faced many problems such as high memory consumption and the inability to modify the construction of the graph. We propose an improved model based on GNN to solve these problems. The model no longer fixes the entire corpus as a graph but constructs different graphs for each text. This method reduces memory consumption, but still retains global information. We conduct experiments on the R8, R52, and 20newsgroups data sets, and use accuracy as the experimental standard. Experiments show that even if it consumes less memory, our model accomplish higher than existing models on multiple text classification data sets.

Estimating the boundary surface between geologic formations from 3D seismic data using neural networks and geostatistics

Geophysics ◽  
2005 ◽  
Vol 70 (1) ◽  
pp. P1-P11 ◽  
Author(s):  
Peter A. Dowd ◽  
Eulogio Pardo-Igúzquiza
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Seismic Data ◽  
Acoustic Impedance ◽  
Boundary Surface ◽  
Boundary Detection ◽  
Geostatistical Simulation ◽  
3D Seismic ◽  
Filter Noise ◽  
3D Seismic Data

The exact locations of horizons that separate geologic sequences are known only at physically sampled locations (e.g., borehole intersections), which, in general, are very sparse. 3D seismic data, on the other hand, provide complete coverage of a volume of interest with the possibility of detecting the boundaries between formations with, for example, contrasted acoustic impedance. Detection of boundaries is hampered, however, by coarse spatial resolution of the seismic data, together with local variability of acoustic impedance within formations. The authors propose a two-part approach to the problem, using neural networks and geostatistics. First, an artificial neural network is used for boundary detection. The training set for the neural net comprises seismic traces that are collocated with the borehole locations. Once the net is trained, it is applied to the entire seismic grid. Second, output from the neural network is processed geostatistically to filter noise and to assess the uncertainty of the boundary locations. A physical counterpart is interpreted for each structure inferred from the spatial semivariogram. Factorial kriging is used for filtering, and uncertainty in the shape of the boundaries is assessed by geostatistical simulation. In this approach, the boundary locations are interpreted as random functions that can be simulated to incorporate their uncertainty in applications. A case study of boundary detection between sandstone and breccia formations in a highly faulted zone is used to illustrate the methodologies.

Approximate computation of the acoustic impedance from seismic data

Geophysics ◽  
1983 ◽  
Vol 48 (10) ◽  
pp. 1351-1358 ◽  
Author(s):  
K. A. Berteussen ◽  
B. Ursin
Keyword(s):  
Seismic Data ◽  
Acoustic Impedance ◽  
Recursive Formula ◽  
Continuous Model ◽  
Low Noise ◽  
Nonlinear Transformation ◽  
Earth Model ◽  
Approximate Computation ◽  
Impedance Function ◽  
Band Limited

The approximate computation of the acoustic impedance from seismic data is usually based on the recursive formula [Formula: see text] where [Formula: see text] is the acoustic impedance in layer number k and [Formula: see text] is the pressure reflection coefficient for the interface between layer k and [Formula: see text]. The above formula is derived from a discrete layered earth model. When we consider a continuous earth model and discretize the results, we obtain the recursive formula [Formula: see text] The two expressions give very similar numerical results. For [Formula: see text], the relative difference is less than 5 percent and this cannot be visually recognized on an acoustic impedance section. The expression for the continuous model is more suitable for understanding the result of the approximate computation of the acoustic impedance function from band‐limited seismic data. The calculated impedance minus the impedance in the top layer is approximately equal to the reflectivity function convolved with the integrated seismic pulse multiplied with twice the impedance in the top layer. For impedance values less than 0.2 in absolute value this is also equal to the acoustic impedance function (minus the acoustic impedance in the top layer) convolved with the seismic pulse. The computation of the acoustic impedance from band‐limited seismic data corresponds to an exponential transformation of the integrated seismic trace. On a band‐limited acoustic impedance section with well‐separated reflectors and low noise level the direction of change in the acoustic impedance can be correctly identified. The effect of additive noise in the seismic data is governed by a nonlinear transformation. Our data examples show that the computation of acoustic impedance becomes unstable when noise is added. In order to avoid the nonlinear transformation of the seismic data, it has been suggested to integrate the seismic data. This results in an estimate of the logarithm of the acoustic impedance. For band‐limited seismic data with noise this gives a band‐limited estimate of the logarithm of the acoustic impedance plus the integrated noise. A disadvantage of this method is that the variance of the integrated noise increases linearly with time.

Sign in / Sign up

Export Citation Format

Share Document