Shengyu Yang
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
Research Subjects
Research Interests
Shengyu Yang has a total of 89 co-authors. Here are the top co-authors by number of shared publications:
Brian Horsfield
7 shared publications- Qinhong Hu
China University of Petroleum (East China)
7 shared publications Hans-Martin Schulz
Department of Geochemistry, Section 3.2 Organic Geochemistry, Helmholtz Centre Potsdam GFZ German Research Centre for Geosciences, Telegrafenberg, D-14473 Potsdam, Germany
5 shared publications- Lu Qiao
National Key Laboratory of Deep Oil and Gas, China University of Petroleum (East China) 1 , Qingdao 266580
4 shared publications Huijun Wang
3 shared publications- Niels Hemmingsen Schovsbo
Geological Survey of Denmark and Greenland (GEUS), Copenhagen K, Denmark
3 shared publications
Latest Publications
- 6 October 2026
- Published by Springer Nature
- p. 34-48
Study on the Microscopic Retention and Migration Characteristics of Shale in Shahejie Formation in Dongying Sag
- 6 October 2026
- Published by Springer Nature
- p. 34-48
Study on the Microscopic Retention and Migration Characteristics of Shale in Shahejie Formation in Dongying Sag
- 1 August 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (8)
An integrated unsupervised–supervised learning framework for enhanced petrophysical prediction
Well logging remains a cornerstone of hydrocarbon reservoir evaluation, yet conventional inversion techniques struggle to accurately characterize complex, heterogeneous formations. Although machine learning offers promising alternatives, our benchmarking of three dominant paradigms—single-model frameworks, single-level ensembles, and dual-level heterogeneous ensembles—reveals persistent performance ceilings due to limited representational capacity and reliance on scarce labeled data. Moreover, existing approaches largely overlook the abundant but unlabeled well logs available in field archives, leading to significant underutilization of geological information. To address these limitations, we propose a novel ensemble framework that integrates unsupervised and supervised learning paradigms for well-log analysis. Specifically, we employ contrastive learning to pretrain representations from 1480 unlabeled well logs, which are subsequently fine-tuned using 194 labeled total organic carbon (TOC) samples. Applied to the NY1 well in the Jiyang Depression (China), our two-stage ensemble demonstrates superior TOC prediction accuracy and generalization compared to all baseline and supervised-only models. This result highlights the value of leveraging unlabeled data to enhance petrophysical inversion, particularly in label-scarce environments. The proposed framework offers a scalable, data-efficient solution for intelligent reservoir characterization and provides critical support for unconventional hydrocarbon exploration.
- 1 August 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (8)
An integrated unsupervised–supervised learning framework for enhanced petrophysical prediction
Well logging remains a cornerstone of hydrocarbon reservoir evaluation, yet conventional inversion techniques struggle to accurately characterize complex, heterogeneous formations. Although machine learning offers promising alternatives, our benchmarking of three dominant paradigms—single-model frameworks, single-level ensembles, and dual-level heterogeneous ensembles—reveals persistent performance ceilings due to limited representational capacity and reliance on scarce labeled data. Moreover, existing approaches largely overlook the abundant but unlabeled well logs available in field archives, leading to significant underutilization of geological information. To address these limitations, we propose a novel ensemble framework that integrates unsupervised and supervised learning paradigms for well-log analysis. Specifically, we employ contrastive learning to pretrain representations from 1480 unlabeled well logs, which are subsequently fine-tuned using 194 labeled total organic carbon (TOC) samples. Applied to the NY1 well in the Jiyang Depression (China), our two-stage ensemble demonstrates superior TOC prediction accuracy and generalization compared to all baseline and supervised-only models. This result highlights the value of leveraging unlabeled data to enhance petrophysical inversion, particularly in label-scarce environments. The proposed framework offers a scalable, data-efficient solution for intelligent reservoir characterization and provides critical support for unconventional hydrocarbon exploration.
- 7 March 2025
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 250
Integrated framework of Total Organic Carbon (TOC) content prediction and application in shale
- 7 March 2025
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 250
Integrated framework of Total Organic Carbon (TOC) content prediction and application in shale
- 1 March 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (3)
Utilizing conditional generative adversarial networks for data augmentation in logging evaluation
Logging is critical for reservoir and fluid characterization by integrating the geophysical properties of rock layers. Traditional evaluation methods struggle with parameter selection, compromising predictive accuracy and generalizability. Machine learning, particularly conditional generative adversarial networks (CGAN), offers a robust alternative, addressing the disparity between labeled and unlabeled logging data that can lead to evaluation discrepancies. This study applies CGAN to augment data, enhancing input features for improved logging interpretation. We implemented this approach in the Jiyang Depression, Eastern China, using a dataset comprising 194 data points, each consisting of 18 logging curve features and one corresponding total organic carbon measurement from well NY1. The methodology aims to bolster the accuracy and reliability of logging interpretations through targeted data augmentation. We validated the augmented data's reliability through comprehensive analysis, including data characteristic assessments, statistical tests, mutual information analysis, similarity measurements, and consistency testing. The results confirm the efficacy of our data enhancement strategy, providing a robust framework for logging interpretation and future reservoir assessment. The method's effectiveness and reliability suggest broad applicability in fields such as seismic assessment and engineering development. This research not only bridges the gap between labeled and unlabeled data but also harnesses advanced machine learning to enhance geophysical evaluation outcomes. It underscores the importance of innovative data augmentation in the advancement of reservoir characterization and geophysical exploration.
- 1 March 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (3)
Utilizing conditional generative adversarial networks for data augmentation in logging evaluation
Logging is critical for reservoir and fluid characterization by integrating the geophysical properties of rock layers. Traditional evaluation methods struggle with parameter selection, compromising predictive accuracy and generalizability. Machine learning, particularly conditional generative adversarial networks (CGAN), offers a robust alternative, addressing the disparity between labeled and unlabeled logging data that can lead to evaluation discrepancies. This study applies CGAN to augment data, enhancing input features for improved logging interpretation. We implemented this approach in the Jiyang Depression, Eastern China, using a dataset comprising 194 data points, each consisting of 18 logging curve features and one corresponding total organic carbon measurement from well NY1. The methodology aims to bolster the accuracy and reliability of logging interpretations through targeted data augmentation. We validated the augmented data's reliability through comprehensive analysis, including data characteristic assessments, statistical tests, mutual information analysis, similarity measurements, and consistency testing. The results confirm the efficacy of our data enhancement strategy, providing a robust framework for logging interpretation and future reservoir assessment. The method's effectiveness and reliability suggest broad applicability in fields such as seismic assessment and engineering development. This research not only bridges the gap between labeled and unlabeled data but also harnesses advanced machine learning to enhance geophysical evaluation outcomes. It underscores the importance of innovative data augmentation in the advancement of reservoir characterization and geophysical exploration.
- 5 December 2024
- Published by American Chemical Society (ACS) in Energy & Fuels
- Vol. 38 (24) , 23447-23465
The Potential of the Oldest Shale Oil in China: Mesoproterozoic Hongshuizhuang and Xiamaling Shales in the Yanshan Basin
- 5 December 2024
- Published by American Chemical Society (ACS) in Energy & Fuels
- Vol. 38 (24) , 23447-23465
The Potential of the Oldest Shale Oil in China: Mesoproterozoic Hongshuizhuang and Xiamaling Shales in the Yanshan Basin
- 5 October 2024
- Published by American Chemical Society (ACS) in Energy & Fuels
- Vol. 38 (20) , 19525-19538
Nuclear Magnetic Resonance-Based Comparative Studies of Centrifugation, N2 flooding, CO2 Huff-n-Puff, and Spontaneous Imbibition for Oil Recovery in Lacustrine Shale in Eastern China
- 5 October 2024
- Published by American Chemical Society (ACS) in Energy & Fuels
- Vol. 38 (20) , 19525-19538
Nuclear Magnetic Resonance-Based Comparative Studies of Centrifugation, N2 flooding, CO2 Huff-n-Puff, and Spontaneous Imbibition for Oil Recovery in Lacustrine Shale in Eastern China
- Open Access
- 5 September 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (9) , 1557
Occurrence Mechanism and Controlling Factors of Shale Oil from the Paleogene Kongdian Formation in Cangdong Sag, Bohai Bay Basin, East China
Free oil, rather than adsorbed oil, is the main contributor to shale oil production with current development technologies, and assessing oil contents in different occurrence states (adsorbed oil vs. free oil) is a critical component in evaluating the economics of shale wells and plays. Although various methodologies have been developed, there are still some fundamental issues in assessing the oil contents in different occurrence states in shale. In this study, a new method was developed to estimate the adsorbed and free oil contents in the Second Member of the Eocene Kongdian Formation (Ek2) shales in Cangdong Sag, Bohai Bay Basin. This method combines the results of standard Rock-Eval pyrolysis and multi-step Rock-Eval pyrolysis with thin section petrography, X-ray diffraction for mineralogy, total organic carbon analyses, field emission scanning electron microscopy for pore morphology, and pore structure analyses by nitrogen physisorption and mercury intrusion porosimetry. Nine lithofacies were identified in a total of 50 shale samples, and the results show that the adsorbed and free oil are mainly contained in pores with diameters > 20 nm, and their contents are mainly controlled by organic matter abundance and thermal maturity of shales. While pore space volume influences the storage of shale oil, it is not a major determinant. Models of shale oil occurrence and its evolution are proposed, suggesting that the high S1 contents of organic-rich and -fair shales, which the latter resulted from oil migration, are the most favorable exploration targets of Ek2 shales. The findings of this study will help prioritize shale oil exploration targets in Ek2 shales.
- 5 September 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (9) , 1557
Open AccessOccurrence Mechanism and Controlling Factors of Shale Oil from the Paleogene Kongdian Formation in Cangdong Sag, Bohai Bay Basin, East China
Free oil, rather than adsorbed oil, is the main contributor to shale oil production with current development technologies, and assessing oil contents in different occurrence states (adsorbed oil vs. free oil) is a critical component in evaluating the economics of shale wells and plays. Although various methodologies have been developed, there are still some fundamental issues in assessing the oil contents in different occurrence states in shale. In this study, a new method was developed to estimate the adsorbed and free oil contents in the Second Member of the Eocene Kongdian Formation (Ek2) shales in Cangdong Sag, Bohai Bay Basin. This method combines the results of standard Rock-Eval pyrolysis and multi-step Rock-Eval pyrolysis with thin section petrography, X-ray diffraction for mineralogy, total organic carbon analyses, field emission scanning electron microscopy for pore morphology, and pore structure analyses by nitrogen physisorption and mercury intrusion porosimetry. Nine lithofacies were identified in a total of 50 shale samples, and the results show that the adsorbed and free oil are mainly contained in pores with diameters > 20 nm, and their contents are mainly controlled by organic matter abundance and thermal maturity of shales. While pore space volume influences the storage of shale oil, it is not a major determinant. Models of shale oil occurrence and its evolution are proposed, suggesting that the high S1 contents of organic-rich and -fair shales, which the latter resulted from oil migration, are the most favorable exploration targets of Ek2 shales. The findings of this study will help prioritize shale oil exploration targets in Ek2 shales.
- 22 August 2024
- Published by Geological Society of London in Journal of the Geological Society
- Vol. 181 (6)
An integrated convolutional neural network prediction framework for in situ shale oil content based on conventional logging data
The quantification of total organic carbon (TOC) and the free hydrocarbon content (S 1 ) is crucial for evaluating the shale oil generation and bearing properties of source rocks. This study aimed to enhance the accuracy of TOC and S 1 quantification in shale oil evaluations. The scope encompassed the development of a novel deep learning framework to overcome the limitations of traditional physical and machine learning or deep learning methods. This paper proposes an integrated swarm optimization algorithm–convolutional neural network/machine learning framework. This framework uses a swarm optimization algorithm for the hyperparameter optimization of a convolutional neural network or machine learning framework, utilizing experimental data from core samples preserved in liquid nitrogen alongside well logging data. The application of the proposed framework to the H11 well in the Subei Basin, China, using 110 core samples, demonstrated a superior performance. The results validate the framework's effectiveness in predicting the TOC and S 1 contents at various depths. The proposed framework stands out for its convenient methodology, wide application range and high precision in prediction. These attributes contribute significantly to the field of petroleum engineering and development, offering a novel approach that promises to enhance both the efficiency and accuracy of well logging evaluation.
- 22 August 2024
- Published by Geological Society of London in Journal of the Geological Society
- Vol. 181 (6)
An integrated convolutional neural network prediction framework for in situ shale oil content based on conventional logging data
The quantification of total organic carbon (TOC) and the free hydrocarbon content (S 1 ) is crucial for evaluating the shale oil generation and bearing properties of source rocks. This study aimed to enhance the accuracy of TOC and S 1 quantification in shale oil evaluations. The scope encompassed the development of a novel deep learning framework to overcome the limitations of traditional physical and machine learning or deep learning methods. This paper proposes an integrated swarm optimization algorithm–convolutional neural network/machine learning framework. This framework uses a swarm optimization algorithm for the hyperparameter optimization of a convolutional neural network or machine learning framework, utilizing experimental data from core samples preserved in liquid nitrogen alongside well logging data. The application of the proposed framework to the H11 well in the Subei Basin, China, using 110 core samples, demonstrated a superior performance. The results validate the framework's effectiveness in predicting the TOC and S 1 contents at various depths. The proposed framework stands out for its convenient methodology, wide application range and high precision in prediction. These attributes contribute significantly to the field of petroleum engineering and development, offering a novel approach that promises to enhance both the efficiency and accuracy of well logging evaluation.
- 26 July 2024
- Published by American Chemical Society (ACS) in Energy & Fuels
- Vol. 38 (16) , 15235-15247
Geological Controlling Factors of Oil Content in the Paleogene Kongdian Formation, Bohai Bay Basin
- 26 July 2024
- Published by American Chemical Society (ACS) in Energy & Fuels
- Vol. 38 (16) , 15235-15247
Geological Controlling Factors of Oil Content in the Paleogene Kongdian Formation, Bohai Bay Basin