Jianfeng Zhang

Jianfeng Zhang


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 May 2022 in Geophysics
Verified
Journal Article
Closed access
KYKai Yang
Kai Yang
XDXingpeng Dong
Xingpeng Dong
XWXiaoyi Wang
Xiaoyi Wang
JZJianfeng Zhang
Jianfeng Zhang
Deprimary reverse time migration (RTM) mitigates the problem of low-wavenumber noise and false events in conventional RTM, and the generation of high-quality angle-domain common-image gathers or angle gathers during deprimary RTM greatly extends its further applications in velocity model updating and subsurface parameter inversion. Poynting-vector-based methods are the most efficient approach to extract angle gathers from RTM or deprimary RTM. However, the instability problem of Poynting-vector-based methods seriously degrades the quality of the generated angle gathers. The instability problem arises from the oscillatory nature of the Poynting vector. To overcome this issue, we propose a novel approach by harnessing the extra simulated Hilbert transformed wavefield in deprimary RTM. Our approach consists of adding the conventional Poynting vector with an ancillary one derived from the Hilbert transformed wavefield, which allows us to eliminate the oscillatory nature of the conventional Poynting vector and obtain a stable algorithm to extract high-quality angle gathers from RTM or deprimary RTM. By using numerical examples with two synthetic data sets and a field data set from the deepwater Gulf of Mexico, we prove the effectiveness of our method in generating high-quality angle gathers.

5 April 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
WLWei Liu
Wei Liu
QCqian cheng
qian cheng
LLLinong Liu
Linong Liu
Yun WangYun Wang
Yun Wang
JZJianfeng Zhang
Jianfeng Zhang
The emerging applications of deep learning in solving geophysical problems have attracted increasing attention. In particular, it is of significance to enhance the computational efficiency of the computationally intensive geophysical algorithms. In this paper, we accelerate deabsorption prestack time migration (QPSTM), which can yield higher-resolution seismic imaging by compensating absorption and correcting dispersion through deep learning. This is implemented by training a neural network with pairs of small-sized patches of the stacked migrated results obtained by conventional PSTM and deabsorption QPSTM and then yielding the high-resolution imaging volume by prediction with the migrated results of conventional PSTM. We use an encoder-decoder network to highlight the features related to high-resolution migrated results in a high-order dimension space. The training data set of small-sized patches not only reduces the required high-resolution migrated result (for instance, only several inline is required) but leads to a fast convergence in training. The proposed deep-learning approach accelerates the high-resolution imaging by more than 100 times. Field data is used to demonstrate the effectiveness of the proposed method.

30 July 2020 in Exploration Geophysics
Verified
Journal Article
Closed access
QCQian Cheng
Qian Cheng
JZJianfeng Zhang
Jianfeng Zhang
WLWei Liu
Wei Liu
Fresnel zones are helpful for obtaining a high signal-to-noise ratio (S/N)-migrated result. A migrated dip-angle gather provides a simple domain for estimating 2D Fresnel zones for 3D migration. We develop a deep-learning-based technology to automatically estimate Fresnel zones from migrated dip-angle gathers, thus avoiding the cumbersome task of manually checking and modifying the boundaries of the Fresnel zones. A pair of 1D Fresnel zones are incorporated to represent a 2D Fresnel zone in terms of the inline and crossline dip angles because it is difficult to directly extract 2D Fresnel zones from a 2D dip-angle gather. The proposed convolutional neural network (CNN) is established by modifying VGGNet. As picking boundaries of the Fresnel zones is a regression problem, we remove the last soft-max layer from the VGGNet. The last three convolution layers and a pooling layer are also removed because the feature maps are small enough. To improve the contrast and definition, we enhance the features of the reflected events in the dip-angle gather. Data normalisation is carried out to accelerate the training process using a simple-rescaling method before training the modified VGGNet. Field data examples demonstrate the effectiveness and efficiency of the proposed method.

1 August 2022 in Geophysics
Verified
Journal Article
Closed access
KYKai Yang
Kai Yang
JZJianfeng Zhang
Jianfeng Zhang
The inverse scattering imaging condition (ISIC) is widely used in reverse time migration (RTM), which naturally eliminates the low-wavenumber noise by combining a time-derivative imaging condition with a spatial-derivative imaging condition. However, when applying ISIC to anisotropic RTM, we observe that the low-wavenumber noise is not entirely eliminated. This phenomenon is the leakage of low-wavenumber noise caused by anisotropy. In anisotropic media, due to the deviation of the vertical velocity from the phase velocity, the spatial-derivative imaging condition does not generate correct weights to cancel the low-wavenumber noise obtained by using the time-derivative imaging condition. By adding an anisotropic correction term to compensate for this deviation, we obtain the anisotropic ISIC, which can fully eliminate the low-wavenumber noise. In addition, we construct the connection between the anisotropic ISIC and the scattering function. The scattering function describes the power of the media to generate the scattering field, and it encompasses the effect of model perturbations and their scattering patterns. Under the small perturbation assumption and weak anisotropy approximation, we theoretically find that the ISIC reverses the scattering process and recovers the scattering function from the scattering field. Through three numerical examples, we determine the effectiveness of our method in suppressing the low-wavenumber noise for anisotropic RTM. The anisotropic ISIC also has potential applications in inversion-based imaging algorithms.


16 June 2024 in Journal of Applied Geophysics
Verified
Journal Article
Closed access
KYKai Yang
Kai Yang
FZFeng Zhu
Feng Zhu
ZLZhengwei Li
Zhengwei Li
JXJincheng Xu
Jincheng Xu
JZJianfeng Zhang
Jianfeng Zhang