Next Article in Journal
Hybrid GNN–Transformer Architectures for Reliable Remaining Useful Life Prediction in Nuclear Power Plants
Previous Article in Journal
Data-Driven Prediction of Caprock Breakthrough Pressure and Permeability for CO2 Storage Integrity: A Meta-Analysis
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Energies
Volume 19
Issue 14
10.3390/en19143360
energies-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Hybrid Deep Learning Approach for Small-Sample TOC Prediction in Saline Lacustrine Shale

by
Bo Yuan
1,2,
Bolin Zhang
1,2,
Yuanhao Zhang
1,2,*,
Jun Zhang
1,2,
Tao Hu
1,2,*,
Nansheng Qiu
1,2,
Zigen Wang
1,2,
Mingming Ma
1,2,
Zhiming Xiong
1,2,
Miao Wang
3,
Zhenxue Jiang
1,2,
Maowen Li
4 and
Xiongqi Pang
1,2
1
State Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing), Beijing 102249, China
2
College of Geosciences, China University of Petroleum (Beijing), Beijing 102249, China
3
School of Geosciences, China University of Petroleum (East China), Qingdao 266580, China
4
Exploration and Development Research Institute, SINOPEC, Beijing 100083, China
*
Authors to whom correspondence should be addressed.
Energies 2026, 19(14), 3360; https://doi.org/10.3390/en19143360
Submission received: 23 April 2026 / Revised: 7 July 2026 / Accepted: 8 July 2026 / Published: 16 July 2026
Browse Figures
Versions Notes

Abstract

Total organic carbon (TOC) is a key parameter for geological sweet spot optimization and resource evaluation. However, accurate TOC prediction remains challenging under small-sample conditions because conventional physical and machine learning methods are commonly limited by insufficient labeled data. To address this problem, this study proposes a hybrid deep learning framework that integrates a convolutional autoencoder with a BP neural network (CAE-BPNN). In this framework, the CAE is first used to learn representative feature expressions from abundant unlabeled logging data, and the learned encoder is then transferred to the supervised prediction stage, where labeled samples are used for TOC prediction through the BPNN. The dataset includes 177 measured TOC samples and 1388 unlabeled logging samples from the Fengcheng Formation shale in Well MY1, in the Mahu Sag, and data from Well MY2 are used for independent validation. Model performance is evaluated using five-fold cross-validation with the coefficient of determination (R2) and root mean square error (RMSE) as metrics. For Well MY1, CAE-BPNN achieves the best performance, with R2 = 0.89 and RMSE = 0.061, outperforming CNN (R2 = 0.85, RMSE = 0.075), GBDT (R2 = 0.83, RMSE = 0.076), RF (R2 = 0.81, RMSE = 0.082), and BPNN (R2 = 0.77, RMSE = 0.085). In the independent validation using Well MY2, CAE-BPNN also shows superior predictive performance, with R2 = 0.81 and RMSE = 0.367. These results indicate that unlabeled logging data can effectively enhance feature representation and improve TOC prediction accuracy under limited labeled-sample conditions. The proposed method provides an effective solution for small-sample TOC prediction and offers a reliable basis for movable oil evaluation using the oil saturation index (OSI), as well as a reference for predicting other geological parameters such as S1, S2, and porosity.
Keywords: small-sample; total organic carbon content; unsupervised learning; convolutional autoencoder; movable oil evaluation small-sample; total organic carbon content; unsupervised learning; convolutional autoencoder; movable oil evaluation

Share and Cite

MDPI and ACS Style

Yuan, B.; Zhang, B.; Zhang, Y.; Zhang, J.; Hu, T.; Qiu, N.; Wang, Z.; Ma, M.; Xiong, Z.; Wang, M.; et al. A Hybrid Deep Learning Approach for Small-Sample TOC Prediction in Saline Lacustrine Shale. Energies 2026, 19, 3360. https://doi.org/10.3390/en19143360

AMA Style

Yuan B, Zhang B, Zhang Y, Zhang J, Hu T, Qiu N, Wang Z, Ma M, Xiong Z, Wang M, et al. A Hybrid Deep Learning Approach for Small-Sample TOC Prediction in Saline Lacustrine Shale. Energies. 2026; 19(14):3360. https://doi.org/10.3390/en19143360

Chicago/Turabian Style

Yuan, Bo, Bolin Zhang, Yuanhao Zhang, Jun Zhang, Tao Hu, Nansheng Qiu, Zigen Wang, Mingming Ma, Zhiming Xiong, Miao Wang, and et al. 2026. "A Hybrid Deep Learning Approach for Small-Sample TOC Prediction in Saline Lacustrine Shale" Energies 19, no. 14: 3360. https://doi.org/10.3390/en19143360

APA Style

Yuan, B., Zhang, B., Zhang, Y., Zhang, J., Hu, T., Qiu, N., Wang, Z., Ma, M., Xiong, Z., Wang, M., Jiang, Z., Li, M., & Pang, X. (2026). A Hybrid Deep Learning Approach for Small-Sample TOC Prediction in Saline Lacustrine Shale. Energies, 19(14), 3360. https://doi.org/10.3390/en19143360

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop