Wyniki wyszukiwania - BazTech

1

P-Impedance and Vp/Vs prediction based on AVO inversion scheme with deep feedforward neural network: a case study from tight sandstone reservoir

Mao Xinjun, Han Xuehui, Wu Baohai, Wang Zhenlin, Zhang Hao, Wang Hongliang

Acta Geophysica

|

2022

|

Vol. 70, no 2

563--580

EN

The low-frequency component of seismic data is an inevitable part to obtain absolute P-impedance (Ip) and Vp∕Vs ratio of the subsurface, especially for the reservoir sweet spot. In this work, we train the deep feedforward neural network (DFNN) with band-pass seismic data and well log data to obtain favorable low-frequency components. Specifically, the Bayesian inference strategy is first applied to the pre-stack constrained sparse spike inversion process, obtaining an “initial” inverted band-pass parameters, which are subsequently used as input when applying the DFNN algorithm to predict low- and bandpass parameters. Moreover, the high linear correlation coefficient between the DFNN-based inversion results and the realistic well logging curves of the blind wells demonstrates that the DFNN-based inversion scheme exhibits strong robustness and good generalization ability. Ultimately, we apply the proposed DFNN-based inversion strategy to a tight sandstone reservoir located at the Sichuan basin field from onshore China. Both low- and band-pass Ip and Vp∕Vs inverted for the clastic formation of the Sichuan basin show a strong correlation with the corresponding Ip and Vp∕Vs logs.

2

Adaptive individual weight-gain AVO inversion with smooth nonconvex regularization

Du Siyuan, Zhang Jiashu, Zhang Sheng, Hu Guangmin

Acta Geophysica

|

2021

|

Vol. 69, no. 4

1199--1213

EN

Amplitude variation with ofset (AVO) inversion is a widely used approach to obtain reliable estimates of elastic parameter in the felds of seismic exploration. However, the AVO inversion is an ill-posed problem because of the band-limited characteristic of seismic data. The regularization constraint plays an important role in improving inversion resolution. Total variation (TV) class regularization based on L1 norm has been introduced in seismic inversion. But, these methods may underestimate the high-amplitude components and obtain low-resolution results. To tackle these issues, we propose to combine a smooth nonconvex regularization approach with adaptive individual weight-gain. Compared with the L1 norm regularizers, the proposed smoothed nonconvex sparsity-inducing regularizers can lead to more accurate estimation for high-amplitude components. Diferent from previous regularization methods, the proposed approach also assigns diferent weight regularization parameters for diferent strata, which we call adaptive individual weight-gain strategy. To ensure sufcient minimization of the constructed objective function, a spectral Polak–Ribière–Polyak conjugate gradient method with line search step size is used. Further, we prove that the proposed algorithm converges to a stationary point. The synthetic data tests illustrate that our approach has improved performance compared with the conventional TV class regularization methods. Field data example further verifes the higher resolution of the proposed approach.

3

Prestack AVO inversion for brittleness index of shale based on BI_Zoeppritz equation and NSGA II

Bi Chenchen, Wang Yanchun, Xie Wei, Sun Wei, Liu Wei

Acta Geophysica

|

2020

|

Vol. 68, no. 4

1067--1082

EN

As one of the evaluation characteristics of shale sweet spots, the brittleness index (BI) of shale formations is of great sig nifcance in predicting the range of sweet spots, and guiding hydraulic fracturing. Based on the three elastic parameters of P-wave velocity (VP), S-wave velocity (VS) and density obtained by conventional prestack AVO inversion, BI can be calcu lated indirectly using the Rickman formula. However, the conventional AVO inversion based on Zoeppritz approximation assumes that incident angle is small and elastic parameters change slowly, which afects the inversion accuracy of the three elastic parameters. Additionally, using these three elastic parameters to obtain BI indirectly also leads to cumulative errors of the inversion results. Therefore, we propose an inversion method based on BI_Zoeppritz equation to directly estimate VP, VS and BI. The BI_Zoeppritz equation is an exact Zoeppritz equation for BI, which is used as the forward operator for the proposed method. The multi-objective function of the inversion method is optimized by a fast nondominated sorting genetic algorithm (NSGA II). An initial model and an optimized search window are used to improve the inversion accuracy. The test results of model data and actual data reveal that this method can directly obtain the BI with high precision. In addition, the stability and noise immunity of the proposed method are verifed by the seismic data with random noise.

4

A robust data driven AVO inversion with logarithm absolute error loss function

Du Siyuan, Zhang Jiashu, Hu Guangmin

Acta Geophysica

|

2020

|

Vol. 68, no. 2

445--458

EN

Amplitude variation with ofset (AVO) inversion is a widely used approach to obtain reliable estimates of elastic parameter. Tikhonov and total variation regularization are commonly used methods to address ill-posed problem of AVO inversion. However, these model-driven methods are only for special geological structure such as smoothness or blockiness. In this letter, a robust data-driven-based regularization method with logarithm absolute error loss function (DDI-Log) for AVO inversion is proposed. In DDI-Log, the information of well-log data and the complex geology are considered in a sparse representation framework. In pre-stack seismic data, outlier noise can negatively infuence inversion results. Thus, diferent from the previous data-driven inversion based on L2 norm loss function, we extend the logarithm absolute error function as the loss function. In the iteration, a new spectral PRP conjugate gradient method is used to solve the large-scale optimization problem. The synthetic data and feld data tests illustrate that the proposed approach is robust against outlier noise and that the resolution and accuracy of the solutions are improved.