Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Acta Geophysica

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

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.

Novel wide-angle AVO attributes using rational function

Xue Yaru, Xiang Jialin, Xu Xin

Acta Geophysica

2020

Vol. 68, no. 1

123--132

Conventional AVO inversion employs Zoeppritz equations and various approximations to them to obtain the refection coeffcients of plane-waves, which are confned to a certain (small) angle range (mostly below 40°). However, near the critical angles (wide-angle), refections at the post-critical angles provide much more potential for velocity and density inversion because of the large amplitudes and phases-shifted waveforms, while the Zoeppritz equations are not applicable anymore. Hence, there is a strong demand for the research into wide-angle AVO. With refection coefcients at wide-angle corresponding to the features of rational function, we try to approximate the seismic data with vector ftting which is used to obtain the rational zero-pole and residual properties of wide-angle AVO. We apply this technique to classify AVO type and recognize the lithology. Our experiment shows that extending our research into wide-angle AVO is very promising in gathering richer data for a more accurate seismic analysis.