Shuai Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shuai Sun has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jianhua Geng
State Key Laboratory of Marine Geology Tongji University Shanghai China
2 shared publications - Luanxiao Zhao
School of Ocean and Earth Sciences, Tongji University, Shanghai 200092, China; Shanghai Key Laboratory of Submarine Resources, Tongji University, Shanghai 200092, China
2 shared publications Zhiliang He
Department of science and technology SINOPEC Beijing China
2 shared publications- Benfeng Wang
State Key Laboratory of Marine Geology Tongji University Shanghai China
1 shared publication - Dong Chen
Petroleum Exploration and Production Research Institute SINOPEC Beijing China
1 shared publication Hong Zhang
Petroleum Exploration and Production Research Institute SINOPEC Beijing China
1 shared publication
Latest Publications
- Open Access
Research and Application of Conditional Generative Adversarial Network for Predicting Gas Content in Deep Coal Seams
Accurate assessment of coalbed methane (CBM) content is essential for characterizing subsurface reservoir distribution, guiding well placement, and estimating reserves. Current methods for determining coal seam gas content mainly rely on direct laboratory measurements of core samples or indirect interpretations derived from well log data. However, conventional coring is costly, while log-based approaches often depend on linear empirical formulas and are restricted to near-wellbore regions. In practice, the relationships between elastic properties and gas content are highly complex and nonlinear, leading conventional linear models to produce substantial prediction errors and inadequate performance. This study introduces a novel method for predicting gas content in deep coal seams using a Conditional Generative Adversarial Network (CGAN). First, elastic parameters are obtained through pre-stack inversion. Next, sensitivity analysis and attribute optimization are applied to identify elastic attributes that are most sensitive to gas content. A CGAN is then employed to learn the nonlinear mapping between multiple fluid-sensitive seismic attributes and gas content distribution. By integrating multiple constraints to refine the discriminator and guide generator training, the model achieves accurate gas content prediction directly from seismic data. Applied to a real dataset from a CBM block in the Ordos Basin, China, the proposed CGAN-based method produces predictions that align closely with measured gas content trends at well locations. Validation at blind wells shows an average prediction error of 1.6 m3/t, with 83% of samples exhibiting errors less than 3 m3/t. This research presents an effective and innovative deep learning approach for predicting coalbed methane content.
Open AccessResearch and Application of Conditional Generative Adversarial Network for Predicting Gas Content in Deep Coal Seams
Accurate assessment of coalbed methane (CBM) content is essential for characterizing subsurface reservoir distribution, guiding well placement, and estimating reserves. Current methods for determining coal seam gas content mainly rely on direct laboratory measurements of core samples or indirect interpretations derived from well log data. However, conventional coring is costly, while log-based approaches often depend on linear empirical formulas and are restricted to near-wellbore regions. In practice, the relationships between elastic properties and gas content are highly complex and nonlinear, leading conventional linear models to produce substantial prediction errors and inadequate performance. This study introduces a novel method for predicting gas content in deep coal seams using a Conditional Generative Adversarial Network (CGAN). First, elastic parameters are obtained through pre-stack inversion. Next, sensitivity analysis and attribute optimization are applied to identify elastic attributes that are most sensitive to gas content. A CGAN is then employed to learn the nonlinear mapping between multiple fluid-sensitive seismic attributes and gas content distribution. By integrating multiple constraints to refine the discriminator and guide generator training, the model achieves accurate gas content prediction directly from seismic data. Applied to a real dataset from a CBM block in the Ordos Basin, China, the proposed CGAN-based method produces predictions that align closely with measured gas content trends at well locations. Validation at blind wells shows an average prediction error of 1.6 m3/t, with 83% of samples exhibiting errors less than 3 m3/t. This research presents an effective and innovative deep learning approach for predicting coalbed methane content.
- 15 May 2023
- Published by Wiley in Geophysical Prospecting
- Vol. 71 (6) , 891-913
Generating complete synthetic datasets for high‐resolution amplitude‐versus‐offset attributes deep learning inversion
Deep learning has been used in seismic exploration to solve seismic inversion problems, however it requires sufficient and diverse training samples and labels to obtain satisfactory results. Insufficient training labels are a common problem since labels usually come from well‐logging data, which are limited and sparsely distributed. This can result in a trained network with poor generalizability. A novel complete synthetic dataset‐driven method utilizing convolutional neural network is presented for seismic amplitude‐versus‐offset attributes P and G inversion. Gaussian simulation sampling with physical constraints is used to generate a complete elastic parameter dataset by traversing the entire elastic parameter model space. By randomly combining elastic parameters from the full elastic parameters model space, sufficient synthetic pre‐stack amplitude‐versus‐offset gathers and attribute datasets are generated for training the convolutional neural network. Compared with the limited real data‐driven convolutional neural network, the complete synthetic dataset‐driven convolutional neural network has better generalizability. Broadband training labels improve the accuracy and resolution of the complete synthetic dataset‐driven convolutional neural network's inversion results beyond that of the conventional least‐square data‐fitting method. The complete synthetic dataset‐driven convolutional neural network is robust for processing noise‐contaminated seismic data, but if the frequency band of the labels for training the network is too wide and the signal‐to‐noise ratio of pre‐stack amplitude‐versus‐offset gathers is too low, the quality of the inversion results will reduce. The Marmousi II model and field data examples show that the novel complete synthetic dataset‐driven convolutional neural network can extract higher‐resolution amplitude‐versus‐offset attributes P and G.
- 15 May 2023
- Published by Wiley in Geophysical Prospecting
- Vol. 71 (6) , 891-913
Generating complete synthetic datasets for high‐resolution amplitude‐versus‐offset attributes deep learning inversion
Deep learning has been used in seismic exploration to solve seismic inversion problems, however it requires sufficient and diverse training samples and labels to obtain satisfactory results. Insufficient training labels are a common problem since labels usually come from well‐logging data, which are limited and sparsely distributed. This can result in a trained network with poor generalizability. A novel complete synthetic dataset‐driven method utilizing convolutional neural network is presented for seismic amplitude‐versus‐offset attributes P and G inversion. Gaussian simulation sampling with physical constraints is used to generate a complete elastic parameter dataset by traversing the entire elastic parameter model space. By randomly combining elastic parameters from the full elastic parameters model space, sufficient synthetic pre‐stack amplitude‐versus‐offset gathers and attribute datasets are generated for training the convolutional neural network. Compared with the limited real data‐driven convolutional neural network, the complete synthetic dataset‐driven convolutional neural network has better generalizability. Broadband training labels improve the accuracy and resolution of the complete synthetic dataset‐driven convolutional neural network's inversion results beyond that of the conventional least‐square data‐fitting method. The complete synthetic dataset‐driven convolutional neural network is robust for processing noise‐contaminated seismic data, but if the frequency band of the labels for training the network is too wide and the signal‐to‐noise ratio of pre‐stack amplitude‐versus‐offset gathers is too low, the quality of the inversion results will reduce. The Marmousi II model and field data examples show that the novel complete synthetic dataset‐driven convolutional neural network can extract higher‐resolution amplitude‐versus‐offset attributes P and G.
- 5 December 2022
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 88 (2) , M87-M103
Prestack seismic inversion for elastic parameters using model-data-driven generative adversarial networks
Model-data-driven (MDD) generative adversarial networks (GANs) using prestack seismic data to estimate elastic parameters are proposed. First, by traverse sampling of elastic parameter model space and Gaussian sampling, a complete elastic parameter data set is generated. Second, several reflection coefficient sequences are constructed to produce synthetic prestack amplitude-versus-angle (AVA) gathers using the Zoeppritz equations. Third, conditional GANs (CGANs) are trained using synthetic data sets to establish a relationship between the synthetic prestack AVA gathers and elastic parameters. By using low-frequency constraints, the absolute values of the elastic parameters from the prestack AVA gathers are computed. To apply the networks trained with synthetic to field seismic data, Gaussian noise is added to the synthetic prestack AVA gathers of the training data set. Synthetic prestack AVA gathers with different signal-to-noise ratios are used to verify the robustness of the proposed method and explore its generalization to field seismic data. By testing MDD-CGANs applied to a 2D elastic parameter model, the inversion results by MDD-CGANs are closer to the true values than those by the limited-data-driven CGANs and fully convolutional networks. By applying MDD-CGANs to field prestack AVA gathers in the Tarim Basin, West China, more accurate and high-resolution results are obtained than those obtained using the conventional prestack amplitude-variation-with-offset elastic parameters inversion approach.
- 5 December 2022
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 88 (2) , M87-M103
Prestack seismic inversion for elastic parameters using model-data-driven generative adversarial networks
Model-data-driven (MDD) generative adversarial networks (GANs) using prestack seismic data to estimate elastic parameters are proposed. First, by traverse sampling of elastic parameter model space and Gaussian sampling, a complete elastic parameter data set is generated. Second, several reflection coefficient sequences are constructed to produce synthetic prestack amplitude-versus-angle (AVA) gathers using the Zoeppritz equations. Third, conditional GANs (CGANs) are trained using synthetic data sets to establish a relationship between the synthetic prestack AVA gathers and elastic parameters. By using low-frequency constraints, the absolute values of the elastic parameters from the prestack AVA gathers are computed. To apply the networks trained with synthetic to field seismic data, Gaussian noise is added to the synthetic prestack AVA gathers of the training data set. Synthetic prestack AVA gathers with different signal-to-noise ratios are used to verify the robustness of the proposed method and explore its generalization to field seismic data. By testing MDD-CGANs applied to a 2D elastic parameter model, the inversion results by MDD-CGANs are closer to the true values than those by the limited-data-driven CGANs and fully convolutional networks. By applying MDD-CGANs to field prestack AVA gathers in the Tarim Basin, West China, more accurate and high-resolution results are obtained than those obtained using the conventional prestack amplitude-variation-with-offset elastic parameters inversion approach.