Deblending is a data processing procedure used to separate the source interferences of blended seismic data,which are obtained by simultaneous sources with random time delays to reduce the cost of seismic acquisition....Deblending is a data processing procedure used to separate the source interferences of blended seismic data,which are obtained by simultaneous sources with random time delays to reduce the cost of seismic acquisition.There are three types of deblending algorithms,i.e.,filtering-type noise suppression algorithm,inversion-based algorithm and deep-learning based algorithm.We review the merits of these techniques,and propose to use a sparse inversion method for seismic data deblending.Filtering-based deblending approach is applicable to blended data with a low blending fold and simple geometry.Otherwise,it can suffer from signal distortion and noise leakage.At present,the deep learning based deblending methods are still under development and field data applications are limited due to the lack of high-quality training labels.In contrast,the inversion-based deblending approaches have gained industrial acceptance.Our used inversion approach transforms the pseudo-deblended data into the frequency-wavenumber-wavenumher(FKK)domain,and a sparse constraint is imposed for the coherent signal estimation.The estimated signal is used to predict the interference noise for subtraction from the original pseudo-deblended data.Via minimizing the data misfit,the signal can be iteratively updated with a shrinking threshold until the signal and interference are fully separated.The used FKK sparse inversion algorithm is very accurate and efficient compared with other sparse inversion methods,and it is widely applied in field cases.Synthetic example shows that the deblending error is less than 1%in average amplitudes and less than-40 dB in amplitude spectra.We present three field data examples of land,marine OBN(Ocean Bottom Nodes)and streamer acquisitions to demonstrate its successful applications in separating the source interferences efficiently and accurately.展开更多
Tight sandstone has become an important area in gas exploration.In this study,we propose a 3D seismic reservoir parameter inversion method for tight gas-bearing sandstone reservoirs using dual neural networks.The firs...Tight sandstone has become an important area in gas exploration.In this study,we propose a 3D seismic reservoir parameter inversion method for tight gas-bearing sandstone reservoirs using dual neural networks.The first network referred to as the inversion network,receives seismic data and predicts reservoir parameters.At well locations,these predictions will be validated based on actual reservoir parameters to evaluate errors.For non-well locations,synthetic seismic data are generated by the application of rock physics forward modeling and seismic reflection coefficient equations.The errors are then calculated by comparing synthetic seismic data with actual seismic data.During the rock physics forward modeling,pseudo reservoir parameters are derived by perturbing the actual reservoir parameters,which are then used to generate pseudo elastic parameters through the modeling.Both the actual and pseudo parameters are then used to train the second network,referred to as the rock physics network.By incorporating the rock physics network,the method effectively alleviates issues such as gradient explosion that may arise from directly integrating rock physics computations into the network,while the inclusion of pseudo parameters enhances the network's generalization capability.The proposed method enables the direct inversion of porosity,clay conte nt,and water saturation from pre-stack seismic data using deep learning,thereby achieving quantitative predictions of reservoir rock physical parameters.The application to the field data from tight sandstone gas reservoirs in southwestern China demonstrates the method has the good capability of indicating the gas-bearing areas and provide high resolution.展开更多
The brittleness index(BI)is crucial for predicting engineering sweet spots and designing fracturing operations in shale oil reservoir exploration and development.Seismic amplitude variation with offset(AVO)inversion i...The brittleness index(BI)is crucial for predicting engineering sweet spots and designing fracturing operations in shale oil reservoir exploration and development.Seismic amplitude variation with offset(AVO)inversion is commonly used to obtain the BI.Traditionally,velocity,density,and other parameters are firstly inverted,and the BI is then calculated,which often leads to accumulated errors.Moreover,due to the limited of well-log data in field work areas,AVO inversion typically faces the challenge of limited information,resulting in not high accuracy of BI derived by existing AVO inversion methods.To address these issues,we first derive an AVO forward approximation equation that directly characterizes the BI in P-wave reflection coefficients.Based on this,an intelligent AVO inversion method,which combines the advantages of traditional and intelligent approaches,for directly obtaining the BI is proposed.A TransUnet model is constructed to establish the strong nonlinear mapping relationship between seismic data and the BI.By incorporating a combined objective function that is constrained by both low-frequency parameters and training samples,the challenge of limited samples is effectively addressed,and the direct inversion of the BI is stably achieved.Tests on model data and applications on field data demonstrate the feasibility,advancement,and practicality of the proposed method.展开更多
Traditional deep learning methods pursue complex and single network architectures without considering the petrophysical relationship between different elastic parameters.The mathematical and statistical significance o...Traditional deep learning methods pursue complex and single network architectures without considering the petrophysical relationship between different elastic parameters.The mathematical and statistical significance of the inversion results may lead to model overfitting,especially when there are a limited number of well logs in a working area.Multitask learning provides an eff ective approach to addressing this issue.Simultaneously,learning multiple related tasks can improve a model’s generalization ability to a certain extent,thereby enhancing the performance of related tasks with an equal amount of labeled data.In this study,we propose an end-to-end multitask deep learning model that integrates a fully convolutional network and bidirectional gated recurrent unit for intelligent prestack inversion of“seismic data to elastic parameters.”The use of a Bayesian homoscedastic uncertainty-based loss function enables adaptive learning of the weight coeffi cients for diff erent elastic parameter inversion tasks,thereby reducing uncertainty during the inversion process.The proposed method combines the local feature perception of convolutional neural networks with the long-term memory of bidirectional gated recurrent networks.It maintains the rock physics constraint relationships among diff erent elastic parameters during the inversion process,demonstrating a high level of prediction accuracy.Numerical simulations and processing results of real seismic data validate the eff ectiveness and practicality of the proposed method.展开更多
The extensive application of pre-stack depth migration has produced huge volumes of seismic data,which allows for the possibility of developing seismic inversions of reservoir properties from seismic data in the depth...The extensive application of pre-stack depth migration has produced huge volumes of seismic data,which allows for the possibility of developing seismic inversions of reservoir properties from seismic data in the depth domain.It is difficult to estimate seismic wavelets directly from seismic data due to the nonstationarity of the data in the depth domain.We conduct a velocity transformation of seismic data to make the seismic data stationary and then apply the ridge regression method to estimate a constant seismic wavelet.The estimated constant seismic wavelet is constructed as a set of space-variant seismic wavelets dominated by velocities at different spatial locations.Incorporating the weighted superposition principle,a synthetic seismogram is generated by directly employing the space-variant seismic wavelets in the depth domain.An inversion workflow based on the model-driven method is developed in the depth domain by incorporating the nonlinear conjugate gradient algorithm,which avoids additional data conversions between the time and depth domains.The impedance inversions of the synthetic and field seismic data in the depth domain show good results,which demonstrates that seismic inversion in the depth domain is feasible.The approach provides an alternative for forward numerical analyses and elastic property inversions of depth-domain seismic data.It is advantageous for further studies concerning the stability,accuracy,and efficiency of seismic inversions in the depth domain.展开更多
Classical multi-channel technology can significantly reduce the pre-stack seismic inversion uncertainty, especially for complex geology such as high dipping structures. However, due to the consideration of complex str...Classical multi-channel technology can significantly reduce the pre-stack seismic inversion uncertainty, especially for complex geology such as high dipping structures. However, due to the consideration of complex structure or reflection features, the existing multi-channel inversion methods have to adopt the highly time-consuming strategy of arranging seismic data trace-by-trace, limiting its wide application in pre-stack inversion. A fast pre-stack multi-channel inversion constrained by seismic reflection features has been proposed to address this issue. The key to our method is to re-characterize the reflection features to directly constrain the pre-stack inversion through a Hadamard product operator without rearranging the seismic data. The seismic reflection features can reflect the distribution of the stratum reflection interface, and we obtained them from the post-stack profile by searching the shortest local Euclidean distance between adjacent seismic traces. Instead of directly constructing a large-size reflection features constraint operator advocated by the conventional methods, through decomposing the reflection features along the vertical and horizontal direction at a particular sampling point, we have constructed a computationally well-behaved constraint operator represented by the vertical and horizontal partial derivatives. Based on the Alternating Direction Method of Multipliers (ADMM) optimization, we have derived a fast algorithm for solving the objective function, including Hadamard product operators. Compared with the conventional reflection features constrained inversion, the proposed method is more efficient and accurate, proved on the Overthrust model and a field data set.展开更多
Pre-stack waveform inversion, by inverting seismic information, can estimate subsurface elastic properties for reservoir characterization, thus effectively guiding exploration. In recent years, nonlinear inversion met...Pre-stack waveform inversion, by inverting seismic information, can estimate subsurface elastic properties for reservoir characterization, thus effectively guiding exploration. In recent years, nonlinear inversion methods, such as standard genetic algorithm, have been extensively adopted in seismic inversion due to its simplicity, versatility, and robustness. However, standard genetic algorithms have some shortcomings, such as slow convergence rate and easiness to fall into local optimum. In order to overcome these problems, the authors present a new adaptive genetic algorithm for seismic inversion, in which the selection adopts regional equilibrium and elite retention strategies are adopted, and adaptive operators are used in the crossover and mutation to implement local search. After applying this method to pre-stack seismic data, it is found that higher quality inversion results can be achieved within reasonable running time.展开更多
Stochastic seismic inversion is the combination of geostatistics and seismic inversion technology which integrates information from seismic records, well logs, and geostatistics into a posterior probability density fu...Stochastic seismic inversion is the combination of geostatistics and seismic inversion technology which integrates information from seismic records, well logs, and geostatistics into a posterior probability density function （PDF） of subsurface models. The Markov chain Monte Carlo （MCMC） method is used to sample the posterior PDF and the subsurface model characteristics can be inferred by analyzing a set of the posterior PDF samples. In this paper, we first introduce the stochastic seismic inversion theory, discuss and analyze the four key parameters： seismic data signal-to-noise ratio （S/N）, variogram, the posterior PDF sample number, and well density, and propose the optimum selection of these parameters. The analysis results show that seismic data S/N adjusts the compromise between the influence of the seismic data and geostatistics on the inversion results, the variogram controls the smoothness of the inversion results, the posterior PDF sample number determines the reliability of the statistical characteristics derived from the samples, and well density influences the inversion uncertainty. Finally, the comparison between the stochastic seismic inversion and the deterministic model based seismic inversion indicates that the stochastic seismic inversion can provide more reliable information of the subsurface character.展开更多
We propose to use a Few-Shot Learning(FSL)method for the pre-stack seismic inversion problem in obtaining a high resolution reservoir model from recorded seismic data.Recently,artificial neural network(ANN)demonstrate...We propose to use a Few-Shot Learning(FSL)method for the pre-stack seismic inversion problem in obtaining a high resolution reservoir model from recorded seismic data.Recently,artificial neural network(ANN)demonstrates great advantages for seismic inversion because of its powerful feature extraction and parameter learning ability.Hence,ANN method could provide a high resolution inversion result that are critical for reservoir characterization.However,the ANN approach requires plenty of labeled samples for training in order to obtain a satisfactory result.For the common problem of scarce samples in the ANN seismic inversion,we create a novel pre-stack seismic inversion method that takes advantage of the FSL.The results of conventional inversion are used as the auxiliary dataset for ANN based on FSL,while the well log is regarded the scarce training dataset.According to the characteristics of seismic inversion(large amount and high dimensional),we construct an arch network(A-Net)architecture to implement this method.An example shows that this method can improve the accuracy and resolution of inversion results.展开更多
Young's modulus and Poisson's ratio are crucial parameters for reservoir characterization and rock brittleness evaluation.Conventional methods often rely on indirect computation or approximations of the Zoeppr...Young's modulus and Poisson's ratio are crucial parameters for reservoir characterization and rock brittleness evaluation.Conventional methods often rely on indirect computation or approximations of the Zoeppritz equations to estimate Young's modulus,which can introduce cumulative errors and reduce the accuracy of inversion results.To address these issues,this paper introduces the analytical solution of the Zoeppritz equation into the inversion process.The equation is re-derived and expressed in terms of Young's modulus,Poisson's ratio,and density.Within the Bayesian framework,we construct an objective function for the joint inversion of PP and PS waves.Traditional gradient-based algorithms often suffer from low precision and the computational complexity.In this study,we address limitations of conventional approaches related to low precision and complicated code by using Circle chaotic mapping,Levy flights,and Gaussian mutation to optimize the quantum particle swarm optimization(QPSO),named improved quantum particle swarm optimization(IQPSO).The IQPSO demonstrates superior global optimization capabilities.We test the proposed inversion method with both synthetic and field data.The test results demonstrate the proposed method's feasibility and effectiveness,indicating an improvement in inversion accuracy over traditional methods.展开更多
On the assumption that the seismic wavelet amplitude spectrum is estimated accurately, a group of wavelets with different phase spectra, regarded as estimated wavelets, are used to implement linear least-squares inver...On the assumption that the seismic wavelet amplitude spectrum is estimated accurately, a group of wavelets with different phase spectra, regarded as estimated wavelets, are used to implement linear least-squares inversion. During inversion, except for the wavelet phase, all other factors affecting inversion results are not taken into account. The inversion results of a sparse reflectivity model （or blocky impedance model） show that： （1） although the synthetic data using inversion results matches well with the original seismic data, the inverted reflectivity and acoustic impedance are different from that of the real model. （2） the inversion result reliability is dependent on the estimated wavelet Z transform root distribution. When the estimated wavelet Z transform roots only differ from that of the real wavelet near the unit circle, the inverted reflectivity and impedance are usually consistent with the real model; （3） although the synthetic data matches well with the original data and the Cauchy norm （or modified Cauchy norm） with a constant damping parameter has been optimized, the inverted results are still greatly different from the real model. Finally, we suggest using the L1 norm, Kurtosis, variation, Cauchy norm with adaptive damping parameter or/and modified Cauchy norm with adaptive damping parameter as evaluation criteria to reduce the bad influence of inaccurate wavelet phase estimation and obtain good results in theory.展开更多
Although the ambiguity of seismic inversion is widely recognized in both theory and practice, so far as a concrete inversion example is concerned, there is not any objective, controllable method or any standard for ho...Although the ambiguity of seismic inversion is widely recognized in both theory and practice, so far as a concrete inversion example is concerned, there is not any objective, controllable method or any standard for how to evaluate and determine its ambiguity and reliability, especially for the high frequency components beyond the effective seismic frequency band. Taking log-constrained impedance inversion as an example, a new appraisal method is proposed on the basis of analyzing a simple geological model. Firstly, the inverted impedance model is transformed to a reflection coefficient series. Secondly, the maximum effective frequency of the real seismic data is chosen as a cutoff point and the reflection coefficient series is decomposed into two components by low-pass and high-pass filters. Thirdly, the geometrical reflection characteristics of the high-frequency components and that of the real seismic data are compared and analyzed. Then, the reliability of the inverted impedance model is appraised according to the similarity of geometrical characteristics between the high-frequency components and the real seismic data. The new method avoids some subjectivity in appraising the inverted result, and helps to enhance the reliability of reservoir prediction by impedance inversion technology.展开更多
The major storage space types in the carbonate reservoir in the Ordovician in the TZ45 area are secondary dissolution caves.For the prediction of caved carbonate reservoir,post-stack methods are commonly used in the o...The major storage space types in the carbonate reservoir in the Ordovician in the TZ45 area are secondary dissolution caves.For the prediction of caved carbonate reservoir,post-stack methods are commonly used in the oilfield at present since pre-stack inversion is always limited by poor seismic data quality and insufficient logging data.In this paper,based on amplitude preserved seismic data processing and rock-physics analysis,pre-stack inversion is employed to predict the caved carbonate reservoir in TZ45 area by seriously controlling the quality of inversion procedures.These procedures mainly include angle-gather conversion,partial stack,wavelet estimation,low-frequency model building and inversion residual analysis.The amplitude-preserved data processing method can achieve high quality data based on the principle that they are very consistent with the synthetics.Besides,the foundation of pre-stack inversion and reservoir prediction criterion can be established by the connection between reservoir property and seismic reflection through rock-physics analysis.Finally,the inversion result is consistent with drilling wells in most cases.It is concluded that integrated with amplitude-preserved processing and rock-physics,pre-stack inversion can be effectively applied in the caved carbonate reservoir prediction.展开更多
Deep learning has achieved great success in a variety of research fields and industrial applications.However,when applied to seismic inversion,the shortage of labeled data severely influences the performance of deep l...Deep learning has achieved great success in a variety of research fields and industrial applications.However,when applied to seismic inversion,the shortage of labeled data severely influences the performance of deep learning-based methods.In order to tackle this problem,we propose a novel seismic impedance inversion method based on a cycle-consistent generative adversarial network(Cycle-GAN).The proposed Cycle-GAN model includes two generative subnets and two discriminative subnets.Three kinds of loss,including cycle-consistent loss,adversarial loss,and estimation loss,are adopted to guide the training process.Benefit from the proposed structure,the information contained in unlabeled data can be extracted,and adversarial learning further guarantees that the prediction results share similar distributions with the real data.Moreover,a neural network visualization method is adopted to show that the proposed CNN model can learn more distinguishable features than the conventional CNN model.The robustness experiments on synthetic data sets show that the proposed method can achieve better performances than other methods in most cases.And the blind-well experiments on real seismic profiles show that the predicted impedance curve of the proposed method maintains a better correlation with the true impedance curve.展开更多
Seismic amplitude variation with offset(AVO) inversion is an important approach for quantitative prediction of rock elasticity,lithology and fluid properties.With Biot-Gassmann's poroelasticity,an improved statist...Seismic amplitude variation with offset(AVO) inversion is an important approach for quantitative prediction of rock elasticity,lithology and fluid properties.With Biot-Gassmann's poroelasticity,an improved statistical AVO inversion approach is proposed.To distinguish the influence of rock porosity and pore fluid modulus on AVO reflection coefficients,the AVO equation of reflection coefficients parameterized by porosity,rock-matrix moduli,density and fluid modulus is initially derived from Gassmann equation and critical porosity model.From the analysis of the influences of model parameters on the proposed AVO equation,rock porosity has the greatest influences,followed by rock-matrix moduli and density,and fluid modulus has the least influences among these model parameters.Furthermore,a statistical AVO stepwise inversion method is implemented to the simultaneous estimation of rock porosity,rock-matrix modulus,density and fluid modulus.Besides,the Laplace probability model and differential evolution,Markov chain Monte Carlo algorithm is utilized for the stochastic simulation within Bayesian framework.Models and field data examples demonstrate that the simultaneous optimizations of multiple Markov chains can achieve the efficient simulation of the posterior probability density distribution of model parameters,which is helpful for the uncertainty analysis of the inversion and sets a theoretical fundament for reservoir characterization and fluid discrimination.展开更多
Comprehensive inversion of logging and seismic data presented in this paper is a method to improve seismic data resolution. It involves using ample high-frequency information and complete low-frequency information of ...Comprehensive inversion of logging and seismic data presented in this paper is a method to improve seismic data resolution. It involves using ample high-frequency information and complete low-frequency information of known logging to make up for the lack of limited bandwidth of practical seismic recording, obtaining an approximate reflection coefficient sequence (or wave impedance) of high resolution by iterative inversion and providing more reliable seismic evidence for further lithologic interpretation and lateral tracking, correlation and prediction of thin reservoir. The comprehensive inversion can be realized in the following steps: (1) to establish an initial model of higher resolution; (2) to obtain wavelets, and (3) to constrain iterative inversion. The key to this inversion lies in building an initial model. It is assumed from our experience that when the initial model is properly given, iterative inversion can be quickly converged to the ideal result.展开更多
Non-liner wave equation inversion,wavelet analysis and artificial neural networks were used to obtain stratum parameters and the distribution of thin coal seams.The lithology of the water-bearing/resisting layer in th...Non-liner wave equation inversion,wavelet analysis and artificial neural networks were used to obtain stratum parameters and the distribution of thin coal seams.The lithology of the water-bearing/resisting layer in the Quaternary system was also predicted.The implementation process included calculating the well log parameters,stratum contrasting the seismic data and the well logs,and extracting,studying and predicting seismic attributes.Seismic inversion parameters,including the layer velocity and wave impedance,were calculated and effectively used for prediction and analysis.Prior knowledge and seismic interpretation were used to remedy a dearth of seismic data during the inversion procedure.This enhanced the stability of the inversion method.Non-linear seismic inversion and artificial neural networks were used to interpret coal seismic lithology and to study the water-bearing/resisting layer in the Quaternary system.Interpretation of the 1～2 m thin coal seams,and also of the water-bearing/resisting layer in the Quaternary system,is provided.The upper mining limit can be lifted from 60 m to 45 m.The predictions show that this method can provide reliable data useful for thin coal seam exploitation and for lifting the upper mining limit,which is one of the principles of green mining.展开更多
Deep learning is widely used for seismic impedance inversion,but few work provides in-depth research and analysis on designing the architectures of deep neural networks and choosing the network hyperparameters.This pa...Deep learning is widely used for seismic impedance inversion,but few work provides in-depth research and analysis on designing the architectures of deep neural networks and choosing the network hyperparameters.This paper is dedicated to comprehensively studying on the significant aspects of deep neural networks that affect the inversion results.We experimentally reveal how network hyperparameters and architectures affect the inversion performance,and develop a series of methods which are proven to be effective in reconstructing high-frequency information in the estimated impedance model.Experiments demonstrate that the proposed multi-scale architecture is helpful to reconstruct more high-frequency details than a conventional network.Besides,the reconstruction of high-frequency information can be further promoted by introducing a perceptual loss and a generative adversarial network from the computer vision perspective.More importantly,the experimental results provide valuable references for designing proper network architectures in the seismic inversion problem.展开更多
To improve the accuracy of inversion results,geological facies distributions are considered as additional constraints in the inversion process.However,the geological facies itself also has its own uncertainty.In this ...To improve the accuracy of inversion results,geological facies distributions are considered as additional constraints in the inversion process.However,the geological facies itself also has its own uncertainty.In this paper,the initial sedimentary facies maps are obtained by integrated geological analysis from well data,seismic attributes,and deterministic inversion results.Then the fi rst iteration of facies-constrained seismic inversion is performed.According to that result and other data such as geological information,the facies distribution can be updated using cluster analysis.The next round of facies-constrained inversion can then be performed.This process will be repeated until the facies inconsistency or error before and after the inversion is minimized.It forms a new iterative facies-constrained seismic inversion technique.Compared with conventional facies-constrained seismic inversion,the proposed method not only can reduces the non-uniqueness of seismic inversion results but also can improves its resolution.As a consequence,the sedimentary facies will be more consistent with the geology.A practical application demonstrated that the superposition relationship of sand bodies could be better delineated based on this new seismic inversion technique.The result highly increases the understanding of reservoir connectivity and its accuracy,which can be used to guide further development.展开更多
With the development of computational power, there has been an increased focus on data-fitting related seismic inversion techniques for high fidelity seismic velocity model and image, such as full-waveform inversion a...With the development of computational power, there has been an increased focus on data-fitting related seismic inversion techniques for high fidelity seismic velocity model and image, such as full-waveform inversion and least squares migration. However, though more advanced than conventional methods, these data fitting methods can be very expensive in terms of computational cost. Recently, various techniques to optimize these data-fitting seismic inversion problems have been implemented to cater for the industrial need for much improved efficiency. In this study, we propose a general stochastic conjugate gradient method for these data-fitting related inverse problems. We first prescribe the basic theory of our method and then give synthetic examples. Our numerical experiments illustrate the potential of this method for large-size seismic inversion application.展开更多
基金supported by National Science and Technology Major Project(Grant No.2017ZX05018-001)。
文摘Deblending is a data processing procedure used to separate the source interferences of blended seismic data,which are obtained by simultaneous sources with random time delays to reduce the cost of seismic acquisition.There are three types of deblending algorithms,i.e.,filtering-type noise suppression algorithm,inversion-based algorithm and deep-learning based algorithm.We review the merits of these techniques,and propose to use a sparse inversion method for seismic data deblending.Filtering-based deblending approach is applicable to blended data with a low blending fold and simple geometry.Otherwise,it can suffer from signal distortion and noise leakage.At present,the deep learning based deblending methods are still under development and field data applications are limited due to the lack of high-quality training labels.In contrast,the inversion-based deblending approaches have gained industrial acceptance.Our used inversion approach transforms the pseudo-deblended data into the frequency-wavenumber-wavenumher(FKK)domain,and a sparse constraint is imposed for the coherent signal estimation.The estimated signal is used to predict the interference noise for subtraction from the original pseudo-deblended data.Via minimizing the data misfit,the signal can be iteratively updated with a shrinking threshold until the signal and interference are fully separated.The used FKK sparse inversion algorithm is very accurate and efficient compared with other sparse inversion methods,and it is widely applied in field cases.Synthetic example shows that the deblending error is less than 1%in average amplitudes and less than-40 dB in amplitude spectra.We present three field data examples of land,marine OBN(Ocean Bottom Nodes)and streamer acquisitions to demonstrate its successful applications in separating the source interferences efficiently and accurately.
基金the supports provided by the CNPC Science and Technology Major Project(Grant Nos.2023ZZ05,2023ZZ0505,2023ZZ18-03)Changqing Oilfield Science and Technology Major Project(Grant No.2023DZZ01)。
文摘Tight sandstone has become an important area in gas exploration.In this study,we propose a 3D seismic reservoir parameter inversion method for tight gas-bearing sandstone reservoirs using dual neural networks.The first network referred to as the inversion network,receives seismic data and predicts reservoir parameters.At well locations,these predictions will be validated based on actual reservoir parameters to evaluate errors.For non-well locations,synthetic seismic data are generated by the application of rock physics forward modeling and seismic reflection coefficient equations.The errors are then calculated by comparing synthetic seismic data with actual seismic data.During the rock physics forward modeling,pseudo reservoir parameters are derived by perturbing the actual reservoir parameters,which are then used to generate pseudo elastic parameters through the modeling.Both the actual and pseudo parameters are then used to train the second network,referred to as the rock physics network.By incorporating the rock physics network,the method effectively alleviates issues such as gradient explosion that may arise from directly integrating rock physics computations into the network,while the inclusion of pseudo parameters enhances the network's generalization capability.The proposed method enables the direct inversion of porosity,clay conte nt,and water saturation from pre-stack seismic data using deep learning,thereby achieving quantitative predictions of reservoir rock physical parameters.The application to the field data from tight sandstone gas reservoirs in southwestern China demonstrates the method has the good capability of indicating the gas-bearing areas and provide high resolution.
基金supposed by the National Nature Science Foundation of China(Grant No.42304131)the Natural Science Foundation of Heilongjiang Province(Grant No.LH2023D012)+1 种基金the Heilongjiang Postdoctoral Fund(Grant No.LBH-Z22092)the Basic Research Fund for Universities in Xinjiang Uygur Autonomous Region(Grant No.XJEDU2023P166)。
文摘The brittleness index(BI)is crucial for predicting engineering sweet spots and designing fracturing operations in shale oil reservoir exploration and development.Seismic amplitude variation with offset(AVO)inversion is commonly used to obtain the BI.Traditionally,velocity,density,and other parameters are firstly inverted,and the BI is then calculated,which often leads to accumulated errors.Moreover,due to the limited of well-log data in field work areas,AVO inversion typically faces the challenge of limited information,resulting in not high accuracy of BI derived by existing AVO inversion methods.To address these issues,we first derive an AVO forward approximation equation that directly characterizes the BI in P-wave reflection coefficients.Based on this,an intelligent AVO inversion method,which combines the advantages of traditional and intelligent approaches,for directly obtaining the BI is proposed.A TransUnet model is constructed to establish the strong nonlinear mapping relationship between seismic data and the BI.By incorporating a combined objective function that is constrained by both low-frequency parameters and training samples,the challenge of limited samples is effectively addressed,and the direct inversion of the BI is stably achieved.Tests on model data and applications on field data demonstrate the feasibility,advancement,and practicality of the proposed method.
基金supported by National Key R&D Program of China(2018YFA0702501)National Natural Science Foundation of China (41974140)+1 种基金Science and Technology Management Department,China National Petroleum Corporation(2022DQ0604-01)China National Petroleum Corporation-China University of Petroleum (Beijing) Strategy。
文摘Traditional deep learning methods pursue complex and single network architectures without considering the petrophysical relationship between different elastic parameters.The mathematical and statistical significance of the inversion results may lead to model overfitting,especially when there are a limited number of well logs in a working area.Multitask learning provides an eff ective approach to addressing this issue.Simultaneously,learning multiple related tasks can improve a model’s generalization ability to a certain extent,thereby enhancing the performance of related tasks with an equal amount of labeled data.In this study,we propose an end-to-end multitask deep learning model that integrates a fully convolutional network and bidirectional gated recurrent unit for intelligent prestack inversion of“seismic data to elastic parameters.”The use of a Bayesian homoscedastic uncertainty-based loss function enables adaptive learning of the weight coeffi cients for diff erent elastic parameter inversion tasks,thereby reducing uncertainty during the inversion process.The proposed method combines the local feature perception of convolutional neural networks with the long-term memory of bidirectional gated recurrent networks.It maintains the rock physics constraint relationships among diff erent elastic parameters during the inversion process,demonstrating a high level of prediction accuracy.Numerical simulations and processing results of real seismic data validate the eff ectiveness and practicality of the proposed method.
基金supported by the National Natural Science Foundation of China(No.41574130,41874143 and 41374134)the National Science and Technology Major Project of China(No.2016ZX05014-001-009)the Sichuan Provincial Youth Science&Technology Innovative Research Group Fund(No.2016TD0023)
文摘The extensive application of pre-stack depth migration has produced huge volumes of seismic data,which allows for the possibility of developing seismic inversions of reservoir properties from seismic data in the depth domain.It is difficult to estimate seismic wavelets directly from seismic data due to the nonstationarity of the data in the depth domain.We conduct a velocity transformation of seismic data to make the seismic data stationary and then apply the ridge regression method to estimate a constant seismic wavelet.The estimated constant seismic wavelet is constructed as a set of space-variant seismic wavelets dominated by velocities at different spatial locations.Incorporating the weighted superposition principle,a synthetic seismogram is generated by directly employing the space-variant seismic wavelets in the depth domain.An inversion workflow based on the model-driven method is developed in the depth domain by incorporating the nonlinear conjugate gradient algorithm,which avoids additional data conversions between the time and depth domains.The impedance inversions of the synthetic and field seismic data in the depth domain show good results,which demonstrates that seismic inversion in the depth domain is feasible.The approach provides an alternative for forward numerical analyses and elastic property inversions of depth-domain seismic data.It is advantageous for further studies concerning the stability,accuracy,and efficiency of seismic inversions in the depth domain.
基金We would like to acknowledge the sponsorship of the National Natural Science Foundation of China(42004092,42030103,41974119)Marine S&T Fund of Shandong Province for Pilot National Laboratory for Marine Science and Technology(Qingdao)(Grant No.2021QNLM020001-6)Young Elite Scientists Sponsorship Program by CAST(2021QNRC001).
文摘Classical multi-channel technology can significantly reduce the pre-stack seismic inversion uncertainty, especially for complex geology such as high dipping structures. However, due to the consideration of complex structure or reflection features, the existing multi-channel inversion methods have to adopt the highly time-consuming strategy of arranging seismic data trace-by-trace, limiting its wide application in pre-stack inversion. A fast pre-stack multi-channel inversion constrained by seismic reflection features has been proposed to address this issue. The key to our method is to re-characterize the reflection features to directly constrain the pre-stack inversion through a Hadamard product operator without rearranging the seismic data. The seismic reflection features can reflect the distribution of the stratum reflection interface, and we obtained them from the post-stack profile by searching the shortest local Euclidean distance between adjacent seismic traces. Instead of directly constructing a large-size reflection features constraint operator advocated by the conventional methods, through decomposing the reflection features along the vertical and horizontal direction at a particular sampling point, we have constructed a computationally well-behaved constraint operator represented by the vertical and horizontal partial derivatives. Based on the Alternating Direction Method of Multipliers (ADMM) optimization, we have derived a fast algorithm for solving the objective function, including Hadamard product operators. Compared with the conventional reflection features constrained inversion, the proposed method is more efficient and accurate, proved on the Overthrust model and a field data set.
基金Supported by the Major Projects of the National Science and Technology of China(No.2016ZX05026-002-003)National Natural Science Foundation of China(No.41374108)
文摘Pre-stack waveform inversion, by inverting seismic information, can estimate subsurface elastic properties for reservoir characterization, thus effectively guiding exploration. In recent years, nonlinear inversion methods, such as standard genetic algorithm, have been extensively adopted in seismic inversion due to its simplicity, versatility, and robustness. However, standard genetic algorithms have some shortcomings, such as slow convergence rate and easiness to fall into local optimum. In order to overcome these problems, the authors present a new adaptive genetic algorithm for seismic inversion, in which the selection adopts regional equilibrium and elite retention strategies are adopted, and adaptive operators are used in the crossover and mutation to implement local search. After applying this method to pre-stack seismic data, it is found that higher quality inversion results can be achieved within reasonable running time.
基金supported by the National Major Science and Technology Project of China on Development of Big Oil-Gas Fields and Coalbed Methane (No. 2008ZX05010-002)
文摘Stochastic seismic inversion is the combination of geostatistics and seismic inversion technology which integrates information from seismic records, well logs, and geostatistics into a posterior probability density function （PDF） of subsurface models. The Markov chain Monte Carlo （MCMC） method is used to sample the posterior PDF and the subsurface model characteristics can be inferred by analyzing a set of the posterior PDF samples. In this paper, we first introduce the stochastic seismic inversion theory, discuss and analyze the four key parameters： seismic data signal-to-noise ratio （S/N）, variogram, the posterior PDF sample number, and well density, and propose the optimum selection of these parameters. The analysis results show that seismic data S/N adjusts the compromise between the influence of the seismic data and geostatistics on the inversion results, the variogram controls the smoothness of the inversion results, the posterior PDF sample number determines the reliability of the statistical characteristics derived from the samples, and well density influences the inversion uncertainty. Finally, the comparison between the stochastic seismic inversion and the deterministic model based seismic inversion indicates that the stochastic seismic inversion can provide more reliable information of the subsurface character.
基金Wupport from the National Natural Science Foundation of China(Grant No.42130812,42174151,and 41804126).
文摘We propose to use a Few-Shot Learning(FSL)method for the pre-stack seismic inversion problem in obtaining a high resolution reservoir model from recorded seismic data.Recently,artificial neural network(ANN)demonstrates great advantages for seismic inversion because of its powerful feature extraction and parameter learning ability.Hence,ANN method could provide a high resolution inversion result that are critical for reservoir characterization.However,the ANN approach requires plenty of labeled samples for training in order to obtain a satisfactory result.For the common problem of scarce samples in the ANN seismic inversion,we create a novel pre-stack seismic inversion method that takes advantage of the FSL.The results of conventional inversion are used as the auxiliary dataset for ANN based on FSL,while the well log is regarded the scarce training dataset.According to the characteristics of seismic inversion(large amount and high dimensional),we construct an arch network(A-Net)architecture to implement this method.An example shows that this method can improve the accuracy and resolution of inversion results.
基金supported by Fundamental Research Funds for the Central Universities,CHD300102264715National Key Research and Development Program of China under Grant 2021YFA0716902Natural Science Basic Research Program of Shaanxi 2024JCYBMS-199。
文摘Young's modulus and Poisson's ratio are crucial parameters for reservoir characterization and rock brittleness evaluation.Conventional methods often rely on indirect computation or approximations of the Zoeppritz equations to estimate Young's modulus,which can introduce cumulative errors and reduce the accuracy of inversion results.To address these issues,this paper introduces the analytical solution of the Zoeppritz equation into the inversion process.The equation is re-derived and expressed in terms of Young's modulus,Poisson's ratio,and density.Within the Bayesian framework,we construct an objective function for the joint inversion of PP and PS waves.Traditional gradient-based algorithms often suffer from low precision and the computational complexity.In this study,we address limitations of conventional approaches related to low precision and complicated code by using Circle chaotic mapping,Levy flights,and Gaussian mutation to optimize the quantum particle swarm optimization(QPSO),named improved quantum particle swarm optimization(IQPSO).The IQPSO demonstrates superior global optimization capabilities.We test the proposed inversion method with both synthetic and field data.The test results demonstrate the proposed method's feasibility and effectiveness,indicating an improvement in inversion accuracy over traditional methods.
基金supported by National Key Basic Research Development Program (Grant No. 2007CB209600)National Major Science and Technology Program (Grant No. 2008ZX05010-002)
文摘On the assumption that the seismic wavelet amplitude spectrum is estimated accurately, a group of wavelets with different phase spectra, regarded as estimated wavelets, are used to implement linear least-squares inversion. During inversion, except for the wavelet phase, all other factors affecting inversion results are not taken into account. The inversion results of a sparse reflectivity model （or blocky impedance model） show that： （1） although the synthetic data using inversion results matches well with the original seismic data, the inverted reflectivity and acoustic impedance are different from that of the real model. （2） the inversion result reliability is dependent on the estimated wavelet Z transform root distribution. When the estimated wavelet Z transform roots only differ from that of the real wavelet near the unit circle, the inverted reflectivity and impedance are usually consistent with the real model; （3） although the synthetic data matches well with the original data and the Cauchy norm （or modified Cauchy norm） with a constant damping parameter has been optimized, the inverted results are still greatly different from the real model. Finally, we suggest using the L1 norm, Kurtosis, variation, Cauchy norm with adaptive damping parameter or/and modified Cauchy norm with adaptive damping parameter as evaluation criteria to reduce the bad influence of inaccurate wavelet phase estimation and obtain good results in theory.
基金supported by the Major Basic Research Development Program of China’s 973 Project(grant No.2007CB209608)the Science and Technology Innovation Foundation of CNPC(grant No.2010D-5006-0301)
文摘Although the ambiguity of seismic inversion is widely recognized in both theory and practice, so far as a concrete inversion example is concerned, there is not any objective, controllable method or any standard for how to evaluate and determine its ambiguity and reliability, especially for the high frequency components beyond the effective seismic frequency band. Taking log-constrained impedance inversion as an example, a new appraisal method is proposed on the basis of analyzing a simple geological model. Firstly, the inverted impedance model is transformed to a reflection coefficient series. Secondly, the maximum effective frequency of the real seismic data is chosen as a cutoff point and the reflection coefficient series is decomposed into two components by low-pass and high-pass filters. Thirdly, the geometrical reflection characteristics of the high-frequency components and that of the real seismic data are compared and analyzed. Then, the reliability of the inverted impedance model is appraised according to the similarity of geometrical characteristics between the high-frequency components and the real seismic data. The new method avoids some subjectivity in appraising the inverted result, and helps to enhance the reliability of reservoir prediction by impedance inversion technology.
基金supported by National Basic Research Program(2006CB202304)of Chinaco-supported by the National Basic Research Program of China(Grant No.2011CB201103)the National Science and Technology Major Project of China(Grant No.2011ZX05004003)
文摘The major storage space types in the carbonate reservoir in the Ordovician in the TZ45 area are secondary dissolution caves.For the prediction of caved carbonate reservoir,post-stack methods are commonly used in the oilfield at present since pre-stack inversion is always limited by poor seismic data quality and insufficient logging data.In this paper,based on amplitude preserved seismic data processing and rock-physics analysis,pre-stack inversion is employed to predict the caved carbonate reservoir in TZ45 area by seriously controlling the quality of inversion procedures.These procedures mainly include angle-gather conversion,partial stack,wavelet estimation,low-frequency model building and inversion residual analysis.The amplitude-preserved data processing method can achieve high quality data based on the principle that they are very consistent with the synthetics.Besides,the foundation of pre-stack inversion and reservoir prediction criterion can be established by the connection between reservoir property and seismic reflection through rock-physics analysis.Finally,the inversion result is consistent with drilling wells in most cases.It is concluded that integrated with amplitude-preserved processing and rock-physics,pre-stack inversion can be effectively applied in the caved carbonate reservoir prediction.
基金financially supported by the NSFC(Grant No.41974126 and 41674116)the National Key Research and Development Program of China(Grant No.2018YFA0702501)the 13th 5-Year Basic Research Program of China National Petroleum Corporation(CNPC)(2018A-3306)。
文摘Deep learning has achieved great success in a variety of research fields and industrial applications.However,when applied to seismic inversion,the shortage of labeled data severely influences the performance of deep learning-based methods.In order to tackle this problem,we propose a novel seismic impedance inversion method based on a cycle-consistent generative adversarial network(Cycle-GAN).The proposed Cycle-GAN model includes two generative subnets and two discriminative subnets.Three kinds of loss,including cycle-consistent loss,adversarial loss,and estimation loss,are adopted to guide the training process.Benefit from the proposed structure,the information contained in unlabeled data can be extracted,and adversarial learning further guarantees that the prediction results share similar distributions with the real data.Moreover,a neural network visualization method is adopted to show that the proposed CNN model can learn more distinguishable features than the conventional CNN model.The robustness experiments on synthetic data sets show that the proposed method can achieve better performances than other methods in most cases.And the blind-well experiments on real seismic profiles show that the predicted impedance curve of the proposed method maintains a better correlation with the true impedance curve.
基金the sponsorship of National Grand Project for Science and Technology(2016ZX05024004,2017ZX05009001,2017ZX05032003)the Fundamental Research Funds for the Central Universities(20CX06036A)+1 种基金the Postdoctoral Applied Research Project of Qingdao(QDYY20190040)the Science Foundation from SINOPEC Key Laboratory of Geophysics(wtyjy-wx2019-01-04)。
文摘Seismic amplitude variation with offset(AVO) inversion is an important approach for quantitative prediction of rock elasticity,lithology and fluid properties.With Biot-Gassmann's poroelasticity,an improved statistical AVO inversion approach is proposed.To distinguish the influence of rock porosity and pore fluid modulus on AVO reflection coefficients,the AVO equation of reflection coefficients parameterized by porosity,rock-matrix moduli,density and fluid modulus is initially derived from Gassmann equation and critical porosity model.From the analysis of the influences of model parameters on the proposed AVO equation,rock porosity has the greatest influences,followed by rock-matrix moduli and density,and fluid modulus has the least influences among these model parameters.Furthermore,a statistical AVO stepwise inversion method is implemented to the simultaneous estimation of rock porosity,rock-matrix modulus,density and fluid modulus.Besides,the Laplace probability model and differential evolution,Markov chain Monte Carlo algorithm is utilized for the stochastic simulation within Bayesian framework.Models and field data examples demonstrate that the simultaneous optimizations of multiple Markov chains can achieve the efficient simulation of the posterior probability density distribution of model parameters,which is helpful for the uncertainty analysis of the inversion and sets a theoretical fundament for reservoir characterization and fluid discrimination.
文摘Comprehensive inversion of logging and seismic data presented in this paper is a method to improve seismic data resolution. It involves using ample high-frequency information and complete low-frequency information of known logging to make up for the lack of limited bandwidth of practical seismic recording, obtaining an approximate reflection coefficient sequence (or wave impedance) of high resolution by iterative inversion and providing more reliable seismic evidence for further lithologic interpretation and lateral tracking, correlation and prediction of thin reservoir. The comprehensive inversion can be realized in the following steps: (1) to establish an initial model of higher resolution; (2) to obtain wavelets, and (3) to constrain iterative inversion. The key to this inversion lies in building an initial model. It is assumed from our experience that when the initial model is properly given, iterative inversion can be quickly converged to the ideal result.
基金Projects 40574057 and 40874054 supported by the National Natural Science Foundation of ChinaProjects 2007CB209400 by the National Basic Research Program of ChinaFoundation of China University of Mining and Technology (OF4471)
文摘Non-liner wave equation inversion,wavelet analysis and artificial neural networks were used to obtain stratum parameters and the distribution of thin coal seams.The lithology of the water-bearing/resisting layer in the Quaternary system was also predicted.The implementation process included calculating the well log parameters,stratum contrasting the seismic data and the well logs,and extracting,studying and predicting seismic attributes.Seismic inversion parameters,including the layer velocity and wave impedance,were calculated and effectively used for prediction and analysis.Prior knowledge and seismic interpretation were used to remedy a dearth of seismic data during the inversion procedure.This enhanced the stability of the inversion method.Non-linear seismic inversion and artificial neural networks were used to interpret coal seismic lithology and to study the water-bearing/resisting layer in the Quaternary system.Interpretation of the 1～2 m thin coal seams,and also of the water-bearing/resisting layer in the Quaternary system,is provided.The upper mining limit can be lifted from 60 m to 45 m.The predictions show that this method can provide reliable data useful for thin coal seam exploitation and for lifting the upper mining limit,which is one of the principles of green mining.
基金supported by the National Natural Science Foundation of China under Grant No.42050104
文摘Deep learning is widely used for seismic impedance inversion,but few work provides in-depth research and analysis on designing the architectures of deep neural networks and choosing the network hyperparameters.This paper is dedicated to comprehensively studying on the significant aspects of deep neural networks that affect the inversion results.We experimentally reveal how network hyperparameters and architectures affect the inversion performance,and develop a series of methods which are proven to be effective in reconstructing high-frequency information in the estimated impedance model.Experiments demonstrate that the proposed multi-scale architecture is helpful to reconstruct more high-frequency details than a conventional network.Besides,the reconstruction of high-frequency information can be further promoted by introducing a perceptual loss and a generative adversarial network from the computer vision perspective.More importantly,the experimental results provide valuable references for designing proper network architectures in the seismic inversion problem.
基金This research is supported by the Joint Funds of the National Natural Science Foundation of China(No.U20B2016)the National Natural Science Foundation of China(No.41874167)the National Natural Science Foundation of China(No.41904130).
文摘To improve the accuracy of inversion results,geological facies distributions are considered as additional constraints in the inversion process.However,the geological facies itself also has its own uncertainty.In this paper,the initial sedimentary facies maps are obtained by integrated geological analysis from well data,seismic attributes,and deterministic inversion results.Then the fi rst iteration of facies-constrained seismic inversion is performed.According to that result and other data such as geological information,the facies distribution can be updated using cluster analysis.The next round of facies-constrained inversion can then be performed.This process will be repeated until the facies inconsistency or error before and after the inversion is minimized.It forms a new iterative facies-constrained seismic inversion technique.Compared with conventional facies-constrained seismic inversion,the proposed method not only can reduces the non-uniqueness of seismic inversion results but also can improves its resolution.As a consequence,the sedimentary facies will be more consistent with the geology.A practical application demonstrated that the superposition relationship of sand bodies could be better delineated based on this new seismic inversion technique.The result highly increases the understanding of reservoir connectivity and its accuracy,which can be used to guide further development.
基金partially supported by the National Natural Science Foundation of China (No.41230318)
文摘With the development of computational power, there has been an increased focus on data-fitting related seismic inversion techniques for high fidelity seismic velocity model and image, such as full-waveform inversion and least squares migration. However, though more advanced than conventional methods, these data fitting methods can be very expensive in terms of computational cost. Recently, various techniques to optimize these data-fitting seismic inversion problems have been implemented to cater for the industrial need for much improved efficiency. In this study, we propose a general stochastic conjugate gradient method for these data-fitting related inverse problems. We first prescribe the basic theory of our method and then give synthetic examples. Our numerical experiments illustrate the potential of this method for large-size seismic inversion application.
