Model-constrained and data-driven double-supervision acoustic impedance inversion

Seismic impedance inversion is an important technique for structure identification and reservoir prediction.Model-based and data-driven impedance inversion are the commonly used inversion methods.In practice,the geophysical inversion problem is essentially an ill-posedness problem,which means that there are many solutions corresponding to the same seismic data.Therefore,regularization schemes,which can provide stable and unique inversion results to some extent,have been introduced into the objective function as constrain terms.Among them,given a low-frequency initial impedance model is the most commonly used regularization method,which can provide a smooth and stable solution.However,this model-based inversion method relies heavily on the initial model and the inversion result is band limited to the effective frequency bandwidth of seismic data,which cannot effectively improve the seismic vertical resolution and is difficult to be applied to complex structural regions.Therefore,we propose a data-driven approach for high-resolution impedance inversion based on the bidirectional long short-term memory recurrent neural network,which regards seismic data as time-series rather than image-like patches.Compared with the model-based inversion method,the data-driven approach provides higher resolution inversion results,which demonstrates the effectiveness of the data-driven method for recovering the high-frequency components.However,judging from the inversion results for characterization the spatial distribution of thin-layer sands,the accuracy of high-frequency components is difficult to guarantee.Therefore,we add the model constraint to the objective function to overcome the shortages of relying only on the data-driven schemes.First,constructing the supervisor1 based on the bidirectional long short-term memory recurrent neural network,which provides the predicted impedance with higher resolution.Then,convolution constraint as supervisor2 is introduced into the objective function to guarantee the reliability and accuracy of the inversion results,which makes the synthetic seismic data obtained from the inversion result consistent with the input data.Finally,we test the proposed scheme based on the synthetic and field seismic data.Compared to model-based and purely data-driven impedance inversion methods,the proposed approach provides more accurate and reliable inversion results while with higher vertical resolution and better spatial continuity.The inversion results accurately characterize the spatial distribution relationship of thin sands.The model tests demonstrate that the model-constrained and data-driven impedance inversion scheme can effectively improve the thin-layer structure characterization based on the seismic data.Moreover,tests on the oil field data indicate the practicality and adaptability of the proposed method.

Model-data-driven P-wave impedance inversion using ResNets and the normalized zero-lag cross-correlation objective function

Model-driven and data-driven inversions are two prominent methods for obtaining P-wave impedance,which is significant in reservoir description and identification.Based on proper initial models,most model-driven methods primarily use the limited frequency bandwidth information of seismic data and can invert P-wave impedance with high accuracy,but not high resolution.Conventional data-driven methods mainly employ the information from well-log data and can provide high-accuracy and highresolution P-wave impedance owing to the superior nonlinear curve fitting capacity of neural networks.However,these methods require a significant number of training samples,which are frequently insufficient.To obtain P-wave impedance with both high accuracy and high resolution,we propose a model-data-driven inversion method using Res Nets and the normalized zero-lag cross-correlation objective function which is effective for avoiding local minima and suppressing random noise.By using initial models and training samples,the proposed model-data-driven method can invert P-wave impedance with satisfactory accuracy and resolution.Tests on synthetic and field data demonstrate the proposed method’s efficacy and practicability.

Seismic fluid identification using a nonlinear elastic impedance inversion method based on a fast Markov chain Monte Carlo method

Elastic impedance inversion with high efficiency and high stability has become one of the main directions of seismic pre-stack inversion. The nonlinear elastic impedance inversion method based on a fast Markov chain Monte Carlo （MCMC） method is proposed in this paper, combining conventional MCMC method based on global optimization with a preconditioned conjugate gradient （PCG） algorithm based on local optimization, so this method does not depend strongly on the initial model. It converges to the global optimum quickly and efficiently on the condition that effi- ciency and stability of inversion are both taken into consid- eration at the same time. The test data verify the feasibility and robustness of the method, and based on this method, we extract the effective pore-fluid bulk modulus, which is applied to reservoir fluid identification and detection, and consequently, a better result has been achieved.

Estimation of fracture density and orientation from azimuthal elastic impedance difference through singular value decomposition

Accurate estimation of fracture density and orientation is of great significance for seismic characterization of fractured reservoirs.Here,we propose a novel methodology to estimate fracture density and orientation from azimuthal elastic impedance(AEI)difference using singular value decomposition(SVD).Based on Hudson's model,we first derive the AEI equation containing fracture density in HTI media,and then obtain basis functions and singular values from the normalized AEI difference utilizing SVD.Analysis shows that the basis function changing with azimuth is related to fracture orientation,fracture density is the linearly weighted sum of singular values,and the first singular value contributes the most to fracture density.Thus,we develop an SVD-based fracture density and orientation inversion approach constrained by smooth prior elastic parameters.Synthetic example shows that fracture density and orientation can be stably estimated,and the correlation coefficient between the true value and the estimated fracture density is above 0.85 even when an S/N ratio of 2.Field data example shows that the estimated fracture orientation is consistent with the interpretation of image log data,and the estimated fracture density reliably indicates fractured gas-bearing reservoir,which could help to guide the exploration and development of fractured reservoirs.

Seismic attributes and integrated prediction of fractured and caved carbonate reservoirs in the Tarim Basin,China

The carbonate reservoirs in the Tarim Basin are characterized by anisotropy and strong heterogeneity.Combined with an integrated analysis of data from seismic,geology,and drilling results,a series of attributes which are suitable for fractured and caved carbonate reservoir prediction is discussed,including amplitude,coherence analysis,spectra decomposition,seismic absorption attenuation analysis and impedance inversion.Moreover,3-D optimization of these attributes is achieved by integration of multivariate discriminant analysis and principle component analysis,where the logging data are taken as training samples.Using the optimized results,the spatial distribution and configuration features of the caved reservoirs can be characterized in detail.This technique not only improves the understanding of the spatial distribution of current reservoirs but also provides a significant basis for the discovery and production of carbonate reservoirs in the Tarim Basin.