共查询到20条相似文献，搜索用时 265 毫秒
1.
G.S. O'Brien 《Geophysical Prospecting》2020,68(6):1758-1770
Seismically derived amplitude-versus-angle attributes along with well constraints are the base inputs into inverting seismic into subsurface properties. Conditioning the common image gathers is a common workflow in quantitative inversion and leads to a more accurate inversion product due to the removal of post-migration artefacts. Here, we apply a neural network to condition the post-migration gathers. The network is a cycle generative adversarial network, CycleGAN, which was designed for image-to-image translation. This can be considered the same problem as translating an artefact rich seismic gather to an artefact free seismic gather. To assess the feasibility of applying the network to pre-stack conditioning, synthetic data sets were generated to train different networks for different tasks. The networks were trained to remove white noise, residual de-multiples, gather flattening and a combination of the above for conditioning. The results show that a trained network was able remove white noise providing a more robust amplitude-versus-offset calculation. Another network trained using synthetic gathers with and without multiples assisted in multiple removal. However, instability around primary preservation has been observed so the network works better as a residual de-multiple method. For gather conditioning, a network was trained with the unpaired artefact-rich and artefact-free training data where the artefacts included complex moveout, noise and multiples. When applied to the test data sets, the networks cleaned the artefact-rich test data and translated complex moveout into flat gathers whilst preserving the amplitude response. Finally, two networks are applied to real data where a gather based on the well logs is used to quantify the match between the conditioned gathers and the raw gathers. The first network used synthetic data to train the network and, when applied to real data, provided a better tie with the well. The second network was trained with synthetic gathers whose properties were constrained by real seismic gathers from near the well. As anticipated, the network trained on the representative training data outperforms the network trained using the unconstrained data. However, the ability of the first network to condition the gather indicates that a sweep of networks can be trained without the need for real data and applied in a manner analogous to the way parameters are adjusted in traditional geophysical methods. The results show that the different neural networks can offer an alternative or augmentation to the existing geophysical workflow for conditioning pre-stack seismic gathers. 相似文献
2.
Separation of diffracted from reflected events in seismic data is still challenging due to the relatively low amplitude of the diffracted wavefield compared to the reflected wavefield as well as the overlap in the kinematics of reflection and diffraction events. A workflow based on deep learning can be a simple and fast alternative, but using training data made by physics-based modelling is expensive and lacks diversity in terms of noise, amplitude, frequency content and wavelet. This results in poor generalization beyond the training data without retraining and transfer learning. In this paper, we demonstrate successful applications of reflection–diffraction separation using a conventional U-net architecture. The novelty of our approach is that we do not use synthetic data created from physics-based modelling, but instead use only synthetic data built from basic geometric shapes. Our domain of application is the pre-migration common-offset domain where reflected events resemble local geology and the diffracted wavefield consists of downward convex hyperbolic diffraction patterns. Both patterns were randomly perturbed in many ways while maintaining their intrinsic features. This approach is inspired by the common practice of data augmentation in deep learning for machine vision applications. Since many of the standard data augmentation techniques lack a geophysical motivation, we have instead perturbed our synthetic training data in ways to make more sense from a signal processing perspective or given our ‘domain knowledge’ of the problem at hand. We did not have to retrain the network to show good results on the field data set. The large variety and diversity in examples enabled to trained neural networks to show encouraging results on synthetic and field data sets that were not used in training. 相似文献
3.
Bayesian inversion of time‐lapse seismic data for the estimation of static reservoir properties and dynamic property changes 
下载免费PDF全文
下载免费PDF全文 Seismic conditioning of static reservoir model properties such as porosity and lithology has traditionally been faced as a solution of an inverse problem. Dynamic reservoir model properties have been constrained by time‐lapse seismic data. Here, we propose a methodology to jointly estimate rock properties (such as porosity) and dynamic property changes (such as pressure and saturation changes) from time‐lapse seismic data. The methodology is based on a full Bayesian approach to seismic inversion and can be divided into two steps. First we estimate the conditional probability of elastic properties and their relative changes; then we estimate the posterior probability of rock properties and dynamic property changes. We apply the proposed methodology to a synthetic reservoir study where we have created a synthetic seismic survey for a real dynamic reservoir model including pre‐production and production scenarios. The final result is a set of point‐wise probability distributions that allow us to predict the most probable reservoir models at each time step and to evaluate the associated uncertainty. Finally we also show an application to real field data from the Norwegian Sea, where we estimate changes in gas saturation and pressure from time‐lapse seismic amplitude differences. The inverted results show the hydrocarbon displacement at the times of two repeated seismic surveys. 相似文献
4.
Artificial neural networks for parameter estimation in geophysics 总被引：12，自引：0，他引：12
5.
Leonardo Azevedo Rúben Nunes Amílcar Soares Guenther Schwedersky Neto Teresa S. Martins 《Geophysical Prospecting》2018,66(Z1):116-131
Seismic inversion plays an important role in reservoir modelling and characterisation due to its potential for assessing the spatial distribution of the sub‐surface petro‐elastic properties. Seismic amplitude‐versus‐angle inversion methodologies allow to retrieve P‐wave and S‐wave velocities and density individually allowing a better characterisation of existing litho‐fluid facies. We present an iterative geostatistical seismic amplitude‐versus‐angle inversion algorithm that inverts pre‐stack seismic data, sorted by angle gather, directly for: density; P‐wave; and S‐wave velocity models. The proposed iterative geostatistical inverse procedure is based on the use of stochastic sequential simulation and co‐simulation algorithms as the perturbation technique of the model parametre space; and the use of a genetic algorithm as a global optimiser to make the simulated elastic models converge from iteration to iteration. All the elastic models simulated during the iterative procedure honour the marginal prior distributions of P‐wave velocity, S‐wave velocity and density estimated from the available well‐log data, and the corresponding joint distributions between density versus P‐wave velocity and P‐wave versus S‐wave velocity. We successfully tested and implemented the proposed inversion procedure on a pre‐stack synthetic dataset, built from a real reservoir, and on a real pre‐stack seismic dataset acquired over a deep‐water gas reservoir. In both cases the results show a good convergence between real and synthetic seismic and reliable high‐resolution elastic sub‐surface Earth models. 相似文献
6.
3D inversion of DC data using artificial neural networks 总被引：2，自引：0，他引：2
Ahmad Neyamadpour W. A. T. Wan Abdullah Samsudin Taib Danesh Niamadpour 《Studia Geophysica et Geodaetica》2010,54(3):465-485
In this paper, we investigate the applicability of artificial neural networks in inverting three-dimensional DC resistivity
imaging data. The model used to produce synthetic data for training the artificial neural network (ANN) system was a homogeneous
medium of resistivity 100 Ωm with an embedded anomalous body of resistivity 1000 Ωm. The different sizes for anomalous body
were selected and their location was changed to different positions within the homogeneous model mesh elements. The 3D data
set was generated using a finite element forward modeling code through standard 3D modeling software. We investigated different
learning paradigms in the training process of the neural network. Resilient propagation was more efficient than any other
paradigm. We studied the effect of the data type used on neural network inversion and found that the use of location and the
apparent resistivity of data points as the input and corresponding true resistivity as the output of networks produces satisfactory
results. We also investigated the effect of the training data pool volume on the inversion properties. We created several
synthetic data sets to study the interpolation and extrapolation properties of the ANN. The range of 100–1000 Ωm was divided
into six resistivity values as the background resistivity and different resistivity values were also used for the anomalous
body. Results from numerous neural network tests indicate that the neural network possesses sufficient interpolation and extrapolation
abilities with the selected volume of training data. The trained network was also applied on a real field dataset, collected
by a pole-pole array using a square grid (8 ×8) with a 2-m electrode spacing. The inversion results demonstrate that the trained
network was able to invert three-dimensional electrical resistivity imaging data. The interpreted results of neural network
also agree with the known information about the investigation area. 相似文献
7.
Valentin Tschannen Norman Ettrich Matthias Delescluse Janis Keuper 《Geophysical Prospecting》2020,68(3):830-844
Diffracted waves carry high-resolution information that can help interpreting fine structural details at a scale smaller than the seismic wavelength. However, the diffraction energy tends to be weak compared to the reflected energy and is also sensitive to inaccuracies in the migration velocity, making the identification of its signal challenging. In this work, we present an innovative workflow to automatically detect scattering points in the migration dip angle domain using deep learning. By taking advantage of the different kinematic properties of reflected and diffracted waves, we separate the two types of signals by migrating the seismic amplitudes to dip angle gathers using prestack depth imaging in the local angle domain. Convolutional neural networks are a class of deep learning algorithms able to learn to extract spatial information about the data in order to identify its characteristics. They have now become the method of choice to solve supervised pattern recognition problems. In this work, we use wave equation modelling to create a large and diversified dataset of synthetic examples to train a network into identifying the probable position of scattering objects in the subsurface. After giving an intuitive introduction to diffraction imaging and deep learning and discussing some of the pitfalls of the methods, we evaluate the trained network on field data and demonstrate the validity and good generalization performance of our algorithm. We successfully identify with a high-accuracy and high-resolution diffraction points, including those which have a low signal to noise and reflection ratio. We also show how our method allows us to quickly scan through high dimensional data consisting of several versions of a dataset migrated with a range of velocities to overcome the strong effect of incorrect migration velocity on the diffraction signal. 相似文献
8.
Within the field of seismic data acquisition with active sources, the technique of acquiring simultaneous data, also known as blended data, offers operational advantages. The preferred processing of blended data starts with a step of deblending, that is separation of the data acquired by the different sources, to produce data that mimic data from a conventional seismic acquisition and can be effectively processed by standard methods. Recently, deep learning methods based on the deep neural network have been applied to the deblending task with promising results, in particular using an iterative approach. We propose an enhancement to deblending with an iterative deep neural network, whereby we modify the training stage of the deep neural network in order to achieve better performance through the iterations. We refer to the method that only uses the blended data as the input data as the general training method. Our new multi-data training method allows the deep neural network to be trained by the data set with the input patches composed of blended data, noisy data with low amplitude crosstalk noise, and unblended data, which can improve the ability of the deep neural network to remove crosstalk noise and protect weak signal. Based on such an extended training data set, the multi-data training method embedded in the iterative separation framework can result in different outputs at different iterations and converge to the best result in a shorter iteration number. Transfer learning can further improve the generalization and separation efficacy of our proposed method to deblend the simultaneous-source data. Our proposed method is tested on two synthetic data and two field data to prove the effectiveness and superiority in the deblending of the simultaneous-source data compared with the general training method, generic noise attenuation network and low-rank matrix factorization methods. 相似文献
9.
随着地震勘探和开发的不断深入，面向地质目标的精细储层预测技术变得越来越重要.由于透射损失、层间多次波、波模式转换以及随机噪声等的影响，观测地震数据和待反演的地下介质属性之间呈现出很强的非线性.考虑到这些非线性，本文基于积分波动方程开展叠前地震反演，从观测地震数据中恢复出介质属性和整体波场，其中反演参数是波动方程中的压缩系数、剪切柔度和密度的对比度，相比于常规线性AVO反演的波阻抗弹性参数，它们对流体指示有更强的敏感性.在反演过程中，从平滑的低频背景场出发，交替迭代求解数据方程和目标方程.采用乘性正则化方法于共轭梯度框架下求解反演参数，采用优化的散射级数Neumann序列获得整体波场，这种方法不易陷入局部极值，能收敛到正确解.测井资料和典型山前带模型测试表明，利用上述反演方法能获得高分辨率的深度域地下介质属性，可直接进行储层预测和解释. 相似文献
10.
In many areas of the world, the presence of shallow high velocity, highly heterogeneous layers complicate seismic imaging of deeper reflectors. Of particular economic interest are areas where potentially hydrocarbon-bearing strata are obscured by layers of basalt. Basalt layers are highly reflective and heterogeneous. Using reflection seismic, top basalt is typified by a high-amplitude, coherent reflector with poor resolution of reflectors below the basalt, and even bottom basalt. Here, we present a new approach to the imaging problem using the pattern recognition abilities of a back-propagation Artificial Neural Network (ANN). ANNs are computational systems that attempt to mimic natural biological neural networks. They have the ability to recognize patterns and develop their own generalizations about a given data set. Back-propagation neural networks are trained on data sets for which the solution is known and tested on the data that are not previously presented to the ANN in order to validate the network result. We show that Artificial Neural Networks, due to their pattern recognition capabilities, can invert the medium statistics based on the seismic character. We produce statistically defined models involving a basalt analogous layer, and calculate full wavefield finite difference synthetic seismograms. We vary basalt layer thickness and source frequency to generate a synthetic model that produces seismic that is similar to real sub-basalt seismic, i.e. high amplitude top basalt reflector and the absence of base basalt and sub-basalt events. Using synthetic shot gathers, generated in a synthetic representation of the sub-basalt case, we can invert the velocity medium standard deviation by using an ANN. By inverting the velocity medium standard deviation, we successfully identified the transition from basalt to sub-basalt on the synthetic shot gathers. We also show that ANNs are capable of identifying the basalt to sub-basalt transition in the presence of incoherent noise. This is important for any future applications of this technique to the real-world seismic data, as this data is never completely noise-free. There is always a certain level of residual (noise remaining after initial noise filtering) environmental/ambient noise present on the recorded seismics, hence, neural network training with noise-free synthetic seismic is less than optimal. 相似文献
11.
Amir Abbas Babasafari Deva Prasad Ghosh Ahmed Mohammed Ahmed Salim Masoumeh Kordi 《Geophysical Prospecting》2020,68(8):2471-2493
Analysis of amplitude variation with offset is an essential step for reservoir characterization. For an accurate reservoir characterization, the amplitude obtained with an isotropic assumption of the reservoir must be corrected for the anisotropic effects. The objective is seismic anisotropic amplitude correction in an effective medium, and, to this end, values and signs of anisotropic parameter differences (Δδ and Δε) across the reflection interfaces are needed. These parameters can be identified by seismic and well log data. A new technique for anisotropic amplitude correction was developed to modify amplitude changes in seismic data in transversely isotropic media with a vertical axis of symmetry. The results show that characteristics of pre-stack seismic data, that is, amplitude variation with offset gradient, can be potentially related to the sign of anisotropic parameter differences (Δδ and Δε) between two layers of the reflection boundary. The proposed methodology is designed to attain a proper fit between modelled and observed amplitude variation with offset responses, after anisotropic correction, for all possible lithofacies at the reservoir boundary. We first estimate anisotropic parameters, that is, δ and ε, away from the wells through Backus averaging of elastic properties resulted from the first pass of isotropic pre-stack seismic inversion, on input data with no amplitude correction. Next, we estimate the anisotropic parameter differences at reflection interfaces (values and signs of Δδ and Δε). We then generate seismic angle gather data after anisotropic amplitude correction using Rüger's equation for the P-P reflection coefficient. The second pass of isotropic pre-stack seismic inversion is then performed on the amplitude-corrected data, and elastic properties are estimated. Final outcome demonstrates how introduced methodology helps to reduce the uncertainty of elastic property prediction. Pre-stack seismic inversion on amplitude-corrected seismic data results in more accurate elastic property prediction than what can be obtained from non-corrected data. Moreover, a new anisotropy attribute (ν) is presented for improvement of lithology identification. 相似文献
12.
本文以提高地震数据的成像质量为目标,提出一种智能的卷积神经网络降噪框架,从带有噪声的地震数据中自适应地学习地震信号。为了加速网络训练和避免训练时出现梯度消失现象,我们在网络中加入残差学习和批标准化的方法,并采用了ReLU激活函数和Adam优化算法优化网络。此外,Marmousi和F3数据集被用来对网络进行训练和测试,经过充分训练的网络不仅能在学习中保留地震数据特征,而且能去除随机噪声。首先充分地训练网络,从中提取出随机噪声,并保留学习到的地震数据特征,之后通过重建地震数据估算测试集中的波形特征。合成记录和实际数据的处理结果显示了深度卷积神经网络在随机噪声压制任务中的潜力,并通过实验验证表明了深度卷积神经网络框架有很好的去噪效果。 相似文献
13.
碳酸盐岩储集层已成为世界石油新发现储量的重要组成部分,识别该类储层对地震数据的信噪比、分辨率以及成像精度提出了更高的要求.本文从地震低频信号缺失的问题出发,首先研究了低频信号缺失对子波、合成地震记录和波阻抗反演的影响,其次分析了深层碳酸盐岩裂缝储层中弱信号低频缺失的特征.针对低频信号缺失问题,本文利用压缩感知理论,并结合反射系数的稀疏特性,提出了自适应计算L1范数权重因子的方法,同时构建了改进的宽带俞式低通整形滤波器,在不影响地震高频信号的同时对地震弱信号进行低频补偿.结果表明,缺失低频信号,会使子波旁瓣变大,合成记录出现假同相轴,厚层波阻抗反演畸变,深层碳酸盐岩裂缝储层弱信号难以识别;而本文方法有效地补偿了深层碳酸盐岩裂缝储层弱信号10Hz以下的频率成分,使得波组反射特征更加清晰,深层弱信号成像质量得到改善,为进一步有效识别深层碳酸盐岩裂缝储层建立了基础. 相似文献
14.
针对随机地震反演中存在的两个主要问题,随机实现含有噪声和难以从大量随机实现中挖掘有效信息,提出了一种基于神经网络的随机地震反演方法.通过对多组随机实现及其正演地震数据的计算,构建了基于序贯高斯模拟的训练集.这也为应用神经网络求解地球物理反问题,提供了一种有效建立训练集的方法.较之传统的神经网络反演,这种训练集不仅保证了学习样本具有多样性,同时还引入了空间相关性.数值模拟结果表明,该方法只需要通过单层前馈神经网络,就可以比较有效的解决一个500个阻抗参数的反演问题. 相似文献
15.
Nonlinear inversion of electrical resistivity imaging using pruning Bayesian neural networks 总被引：1，自引：0，他引：1
Conventional artificial neural networks used to solve electrical resistivity imaging (ERI) inversion problem suffer from overfitting and local minima. To solve these problems, we propose to use a pruning Bayesian neural network (PBNN) nonlinear inversion method and a sample design method based on the K-medoids clustering algorithm. In the sample design method, the training samples of the neural network are designed according to the prior information provided by the K-medoids clustering results; thus, the training process of the neural network is well guided. The proposed PBNN, based on Bayesian regularization, is used to select the hidden layer structure by assessing the effect of each hidden neuron to the inversion results. Then, the hyperparameter α k , which is based on the generalized mean, is chosen to guide the pruning process according to the prior distribution of the training samples under the small-sample condition. The proposed algorithm is more efficient than other common adaptive regularization methods in geophysics. The inversion of synthetic data and field data suggests that the proposed method suppresses the noise in the neural network training stage and enhances the generalization. The inversion results with the proposed method are better than those of the BPNN, RBFNN, and RRBFNN inversion methods as well as the conventional least squares inversion. 相似文献
16.
基于GA-BP理论的储层视裂缝密度地震非线性反演方法 总被引：2，自引：7，他引：2
基于GA-BP理论,将自适应遗传算法与人工神经网络技术(BP算法)有机地相结合,形成了一种储层裂缝自适应遗传-神经网络反演方法.这种新的方法是由编码、适应度函数、遗传操作及混合智能学习等组成,即在成像测井裂缝密度数据约束下,通过对目标问题进行编码(称染色体),然后对染色体进行选择、交叉和变异等遗传操作,使染色体不断进化,从而快速获得全局最优解.在反演执行过程中,利用地震数据和成像测井裂缝密度数据之间的非线性映射关系建立训练样本,将GA算法与BP算法有机地结合,优化三层前向网络参数;或将GA与ANFIS相结合,优化ANFIS网络参数.并采用GA算法与TS算法(Tabu Search)相结合的自适应混合学习算法,该学习算法自始至终将GA和BP两种算法按一定的概率比例进行,其概率自适应变化,以达到混合算法的均衡.这种混合算法提高了网络的收敛速度和精度.我们分别利用两个研究地区的6井和1井成像测井裂缝密度数据与地震数据之间的非线性映射关系建立训练样本,对过这两口井的测线的地震数据进行反演,获得了视裂缝密度剖面,视裂缝密度剖面上裂缝分布特征符合沉积相分布特征和岩石力学性质的变化特征.这种视裂缝密度剖面含有储层裂缝的定量信息,其误差可为油气勘探开发实际要求所允许.因此,这种新的方法优于只能作裂缝定性分析的常规裂缝地震预测方法,具有广阔的应用前景. 相似文献
17.
储层物性参数作为描述储层特性、储层建模和流体模式的重要指标,其准确估算可以为储层预测提供有力参考依据,但传统储层物性参数反演方法无法兼顾反演精度及空间连续性。针对上述问题,本文引入地震属性作为深度学习算法输入,针对地震属性之间存在的信息冗余特征,利用随机森林-递归消除法对地震属性进行约简预处理,最终建立一种基于地震属性约简的储层物性参数预测方法。实际数据测试结果表明,地震属性约简的深度学习储层物性参数预测结果具有良好的精度及横向分辨率,证实本文方法的有效性。 相似文献
18.
Analysis of time‐lapse travel‐time and amplitude changes to assess reservoir compartmentalization 下载免费PDF全文
下载免费PDF全文 Fluid depletion within a compacting reservoir can lead to significant stress and strain changes and potentially severe geomechanical issues, both inside and outside the reservoir. We extend previous research of time‐lapse seismic interpretation by incorporating synthetic near‐offset and full‐offset common‐midpoint reflection data using anisotropic ray tracing to investigate uncertainties in time‐lapse seismic observations. The time‐lapse seismic simulations use dynamic elasticity models built from hydro‐geomechanical simulation output and a stress‐dependent rock physics model. The reservoir model is a conceptual two‐fault graben reservoir, where we allow the fault fluid‐flow transmissibility to vary from high to low to simulate non‐compartmentalized and compartmentalized reservoirs, respectively. The results indicate time‐lapse seismic amplitude changes and travel‐time shifts can be used to qualitatively identify reservoir compartmentalization. Due to the high repeatability and good quality of the time‐lapse synthetic dataset, the estimated travel‐time shifts and amplitude changes for near‐offset data match the true model subsurface changes with minimal errors. A 1D velocity–strain relation was used to estimate the vertical velocity change for the reservoir bottom interface by applying zero‐offset time shifts from both the near‐offset and full‐offset measurements. For near‐offset data, the estimated P‐wave velocity changes were within 10% of the true value. However, for full‐offset data, time‐lapse attributes are quantitatively reliable using standard time‐lapse seismic methods when an updated velocity model is used rather than the baseline model. 相似文献
19.
Timo Lähivaara Alireza Malehmir Antti Pasanen Leo Kärkkäinen Janne M.J. Huttunen Jan S. Hesthaven 《Geophysical Prospecting》2019,67(8):2115-2126
Convolutional neural networks can provide a potential framework to characterize groundwater storage from seismic data. Estimation of key components, such as the amount of groundwater stored in an aquifer and delineate water table level, from active-source seismic data are performed in this study. The data to train, validate and test the neural networks are obtained by solving wave propagation in a coupled poroviscoelastic–elastic media. A discontinuous Galerkin method is applied to model wave propagation, whereas a deep convolutional neural network is used for the parameter estimation problem. In the numerical experiment, the primary unknowns estimated are the amount of stored groundwater and water table level, while the remaining parameters, assumed to be of less of interest, are marginalized in the convolutional neural network-based solution. Results, obtained through synthetic data, illustrate the potential of deep learning methods to extract additional aquifer information from seismic data, which otherwise would be impossible based on a set of reflection seismic sections or velocity tomograms. 相似文献
20.
3D地震数据不规则采样缺失重建是地震勘探数据处理流程中的重要问题.本文提出了一种基于具有保幅特性的非均匀高阶抛物Radon变换（NHOPRT）地震数据重建方法.在最小二乘反演方程中引入Delaunay三角网格剖分来计算空间不规则加权系数,从而获得最接近完整规则数据的高阶抛物Radon变换域系数.在用SVD求解反演方程过程中,利用高阶抛物Radon变换算子在频率域为指数函数,具有线性可分解特性,将二维空间的高阶抛物Radon变换算子分解为两个独立的一维空间变换算子,减小了变换算子的矩阵大小,从而很大程度地提高了计算效率.理论模型和实际地震数据重建测试证明了本文方法的有效性以及实用性. 相似文献