Wenjing Sang

Wenjing Sang

Auto-generated profile, based on publicly available information

Wenjing Sang

PetroChina Planning and Engineering Institute, Beijing, China

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
2 November 2021 in Geophysics
Verified
Journal Article
Closed access
Sanyi YuanSanyi Yuan
Sanyi Yuan
XJXinqi Jiao
Xinqi Jiao
YLYaneng Luo
Yaneng Luo
WSWenjing Sang
Wenjing Sang
SWShangxu Wang
Shangxu Wang
Low-frequency information is important in reducing the nonuniqueness of absolute impedance inversion and for quantitative seismic interpretation. In traditional model-driven impedance inversion methods, the low-frequency impedance background is from an initial model and is almost unchanged during the inversion process. Moreover, the inversion results are limited by the quality of the modeled seismic data and the extracted wavelet. To alleviate these issues, we have investigated a double-scale supervised impedance inversion method based on the gated recurrent encoder-decoder network (GREDN). We first train the decoder network of GREDN called the forward operator, which can map impedance to seismic data. We then implement the well-trained decoder as a constraint to train the encoder network of GREDN called the inverse operator. Besides matching the output of the encoder with broadband pseudowell impedance labels, data generated by inputting the encoder output into the known decoder match the observed narrowband seismic data. The broadband impedance information and the already-trained decoder largely limit the solution space of the encoder. Finally, after training, only the derived optimal encoder is applied to unseen seismic traces to yield broadband impedance volumes. Our approach is fully data driven and does not involve the initial model, seismic wavelet, and model-driven operator. Tests on the Marmousi model illustrate that our double-scale supervised impedance inversion method can effectively recover low-frequency components of the impedance model, and we determine that low frequencies of the predicted impedance originate from well logs. Furthermore, we apply the strategy of combining the double-scale supervised impedance inversion method with a model-driven impedance inversion method to process field seismic data. Tests on a field data set indicate that the predicted impedance results not only reveal a classic tectonic sedimentation history but also match the corresponding results measured at the locations of two wells.

24 September 2022 in Geophysical Journal International
Verified
Journal Article
Closed access
PDF file
WSWenjing Sang
Wenjing Sang
Sanyi YuanSanyi Yuan
Sanyi Yuan
HHHongwei Han
Hongwei Han
HLHaojie Liu
Haojie Liu
YYYue Yu
Yue Yu
SUMMARY: Porosity characterization is of profound significance for seismic inversion and hydrocarbon prediction. Although semi-supervised learning (SSL) based methods have been used to boost prediction accuracy and lateral continuity of supervised learning (SL) inverted subsurface properties, their variations are relatively limited since the relationships between the data and the parameter model are straightforward in most reported cases. To further figure out their essential differences, we proposed the SSL-based network (SSLBN) for reservoir porosity prediction using seismic and well log data with disparate complexity and quality, and compared it with the SL-based network (SLBN). The SSLBN comprises a data-driven inverse model named decoder and a data-driven forward model named encoder based on the bidirectional-gated recurrent units. The architecture of the SLBN is the same as the encoder. Trained by several seismic-to-well pairs and numerous unlabelled seismic logs, the SSLBN learns the physical process from input single-trace observed seismic log to the intermediate porosity log, and the inverted porosity to the output generated seismic log. We first prepare the porosity model with biased or unbiased labels, the convolution model (CM) and reverse time migration (RTM) based synthetic seismic data, and then implement SL- and SSL-based statistical tests. The synthetic data examples demonstrate that the SSLBN has significant preponderance over the SLBN in the scenes of the RTM imaged seismic data and biased porosity labels. Compared with the SLBN, the physical regularization of the data misfit in the SSLBN improves estimation accuracy and reduces prediction uncertainty of porosity. Finally, statistical tests on a braided river deposited field data example illustrate that the SSLBN can generate more geologically trustworthy porosity models and indicate the oil layers of high porosity sandstone reservoirs.

20 July 2020 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
WSWenjing Sang
Wenjing Sang
Sanyi YuanSanyi Yuan
Sanyi Yuan
XYXueshan Yong
Xueshan Yong
XJXinqi Jiao
Xinqi Jiao
SWShangxu Wang
Shangxu Wang
Noise attenuation has been a long-standing but still active topic in seismic data processing. The deep convolutional neural networks (CNNs) have been recently adopted to remove the learned random noise from noisy seismic data, but it is still difficult to improve the generalization ability of learned denoisers due to the limited diversity of training data sets. In this letter, we investigate an end-to-end deep denoising CNNs (DCNNs) with a novel data generation method involving multidimensional geological structure features for seismic denoising. To learn an optimized network denoiser, seismic amplitude data are extracted from 3-D synthetic seismic data along three directions (i.e., two spatial directions and one temporal direction) to prepare a training data set. Compared with using seismic data from only a certain single direction to generate all training samples, this strategy enables DCNNs to learn abundant geological structural information from three directions, and helps DCNNs have a better performance on noise reduction. Another 3-D synthetic seismic data and 3-D real land data examples with plentiful faults and fluvial channels are used to illustrate that the optimized network denoiser can be directly extended to attenuate random noise. The denoising results demonstrate that DCNNs learned from the multidimensional geological structures can accomplish the self-adaptive random noise attenuation, and meanwhile preserve spatial geological structures.

27 June 2022 in Geophysical Prospecting
Verified
Journal Article
Closed access
JMJinyu Meng
Jinyu Meng
SWShoudong Wang
Shoudong Wang
GNGuohua Niu
Guohua Niu
WSWenjing Sang
Wenjing Sang
WGWeiheng Geng
Weiheng Geng
WCWanli Cheng
Wanli Cheng

19 June 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Sanyi YuanSanyi Yuan
Sanyi Yuan
YYYue Yu
Yue Yu
WSWenjing Sang
Wenjing Sang
RXRenjun Xie
Renjun Xie
CZChangsuo Zhou
Changsuo Zhou
SCShuai Chen
Shuai Chen
Seismic horizon interpretation is a fundamental task in subsurface exploration, essential for understanding formation geometry, characterizing reservoir properties, and supporting drilling operations. Traditional methods and deep learning (DL)-based approaches often face challenges in complex geological settings, leading to potential instability or failure in horizon picking. To overcome these challenges, we propose a novel method that integrates deep learning with multiple seismic attributes for robust horizon interpretation. Initially, a sparse horizon grid is constructed, guided by well log data and incorporating geological knowledge, such as structural and sedimentary system information. Using the structural similarity criterion, we select key seismic attributes that effectively distinguish horizon and non-horizon features, enabling neural networks to learn horizon patterns more accurately. The developed horizon picking network establishes a nonlinear mapping between the selected attributes and horizon classification results, improving interpretation accuracy. The proposed method is demonstrated on 3D seismic data from the Bohai Bay Basin, where it successfully provides high-density lateral interpretations of multiple horizons with varying levels of complexity. In addition to this, the method is applied to an ongoing drilling well. The prediction of the deep Archaean buried hill interface, 165 m ahead of the drill bit, showed a depth error of 2.64‰. This approach enhances both the accuracy and reliability of seismic horizon interpretation, making it a valuable tool for supporting safe and efficient drilling in complex geological formations.