Wyniki wyszukiwania - BazTech

Ograniczanie wyników

3 Acta Geophysica

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: deblending

Sortuj według:

Ogranicz wyniki do:

Unsupervised seismic data deblending based on the convolutional autoencoder regularization

Xue Yaru, Chen Yuyao, Jiang Minhui, Duan Hanting, Niu Libo, Chen Chong

Acta Geophysica

2022

Vol. 70, no 3

1171--1182

Simultaneous source technology can provide high-quality seismic data with lower acquisition costs. However, a deblending algorithm is needed to suppress the blending noise. The supervised deep learning methods are effective, but are usually limited by the lack of labels. To solve the problem, we propose an unsupervised deep learning method based on acquisition system. A convolutional autoencoder (CAE) network is employed to predict the deblending results of the input pseudodeblended data. And then, the deblending results will be re-blended using the given blending operator. The parameters of CAE will be optimized by the difference between re-blended data and input data, which is defined as ‘blending loss.’ The blending problem is ill-posed but the CAE can be regarded as an implicit regularization term which constrains the solving process to obtain the desire solution. A numerical test on synthetic data demonstrates that the proposed method can converge to correct results and two field data experiments verify the flexibility and effectiveness of our model. The transfer training method is also used to improve model performance.

Adaptive iterative deblending of simultaneous source seismic data based on sparse inversion

Wei Yajie, Cao Jingjie, Huang Xiaogang, Chen Xue, Cai Zhicheng

Acta Geophysica

2021

Vol. 69, no. 2

497--507

Deblending of simultaneous-source seismic data is becoming more popular in seismic exploration since it can greatly improve the efciency of seismic acquisition and reduce acquisition cost. At present, the deblending methods of simultaneous-source seismic data are mainly divided into two types: fltering method and sparse inversion method. Compared with the fltering method, the sparse inversion method has higher precision, but the selection of its parameter value mainly depends on experience, which is not suitable for large-scale seismic data processing. In this paper, an adaptive iterative deblending method based on sparse inversion is proposed. By improving the original iterative solution method of regularization inversion model, the efective signal and blending noise are weakened simultaneously in the iterative process, so that the energy intensity of blending noise is consistent with that of the efective signal in each iterative, so as to ensure the consistency of the regular parameter calculation method of each iteration. By analyzing the distribution of coefcients in the curvelet domain of pseudo-deblending data and blending noise, it is concluded that the value of regular parameters is the maximum amplitude of residual pseudo-deblending data in the curvelet domain multiplied by a coefcient between 0 and 1. In the process of iterative deblending, the regularized parameters are obtained adaptively from the data itself. It not only ensures the accuracy of the calculation results, but also improves the calculation efciency, which is suitable for large-scale seismic data processing.

Deblending of Simultaneous-source Seismic Data using Fast Iterative Shrinkage-thresholding Algorithm with Firm-thresholding

Qu S., Zhou H., Liu R., Chen Y., Zu S., Yu S., Yuan J., Yang Y.

Acta Geophysica

2016

Vol. 64, no. 4

1064--1092

In this paper, an improved algorithm is proposed to separate blended seismic data. We formulate the deblending problem as a regularization problem in both common receiver domain and frequency domain. It is suitable for different kinds of coding methods such as random time delay discussed in this paper. Two basic approximation frames, which are iterative shrinkage-thresholding algorithm (ISTA) and fast iterative shrinkage-thresholding algorithm (FISTA), are compared. We also derive the Lipschitz constant used in approximation frames. In order to achieve a faster convergence and higher accuracy, we propose to use firm-thresholding function as the thresholding function in ISTA and FISTA. Two synthetic blended examples demonstrate that the performances of four kinds of algorithms (ISTA with soft- and firm-thresholding, FISTA with soft- and firm-thresholding) are all effective, and furthermore FISTA with a firm-thresholding operator exhibits the most robust behavior. Finally, we show one numerically blended field data example processed by FISTA with firm-thresholding function.