THERMAL SCIENCE

International Scientific Journal

Yuxuan Zhao

,

Yong Guo

,

Hao Chen

,

Lei Yang

,

Chuanming Xi

,

Yuqiang Xu

A METHOD FOR LOGGING DATA RECONSTRUCTION BASED ON TRANSFER LEARNING

ABSTRACT
This paper proposes a logging data reconstruction method based on migration learning, which can reduce the dependence on labeled data and also help to im­prove the generalization ability of data-driven models. Reconstruction experiments are carried out using data from a block in the Junggar Basin of Xinjiang, and compared with the conventional data-driven long short-term memory network and recurrent neural network methods. The results show that the reconstruction results based on migration learning improve the accuracy by 21%, which is significantly better than the remaining two methods, and proves the feasibility of the method.
KEYWORDS
logging data reconstruction, transfer learning, Data-driven
PAPER SUBMITTED: 2024-03-24
PAPER REVISED: 2024-03-29
PAPER ACCEPTED: 2024-05-11
PUBLISHED ONLINE: 2024-09-28
DOI REFERENCE: https://doi.org/10.2298/TSCI2404451Z
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2024, VOLUME 28, ISSUE No. 4, PAGES [3451 - 3456]
REFERENCES
[1] Yong, S., et al., Logging Data Processing and Comprehensive Interpretation, China University of Petroleum Press, Dongying, China, 2007
[2] Zhang, L., et al., Well Data-Driven Thin Interlayer Reservoir Prediction Technique in the Bohai a Oilfield, Xinjiang Oil and Gas, 17 (2021), 2, pp. 7-12
[3] Yang, W., et al., Oil Logging Reservoir Recognition Based on TCN and SA-BiLSTM Deep Learning Method, Engineering Applications of Artificial Intelligence, 121 (2023), 1, 105950, 10.1016/j.engappai.2023.105950
[4] Liu, J.-J., et al., Integrating Deep Learning and Logging Data Analytics for Lithofacies Classification and 3-D Modelling of Tight Sandstone Reservoirs, Geoscience Frontiers, 13 (2022), 1, ID101311, 10.1016/j.gsf.2021.101311
[5] Xie, X., et al., A Systematic Study of Borehole Quality Evaluation, Xinjiang Oil and Gas, 16 (2020), 2, pp. 33-37
[6] Wang, J., et al., Logging Curve Prediction Based on a CNN-GRU Neural Network, Geophysical Prospecting for Petroleum, 61 (2022), 2, pp. 276-285
[7] He, X., et al., Log Facies Recognition Based on Convolutional Neural Network, Oil Geophysical Prospecting, 54 (2019), 5, pp. 1159-1165
[8] Kuang, L., et al., Application and Development Trend of Artificial Intelligence in Petroleum Exploration and Development, Petroleum Exploration and Development, 48 (2021), 1, pp. 1-11, 10.1016/s1876-3804(21)60001-0
[9] Huang, X., et al., An Exploration of the Conditions for the Application of Garden's Formula, Xinjiang Petroleum Geology, 3 ( 2000), 3, pp. 233-234
[10] Chen, G., et al., Application of Faust Equation in Rebuilding of Acoustic Curve, Progress in Exploration Geophysics, 26 (2005), 2, pp. 125-128
[11] Kong, Y., et al., Application of Interpolating Based on Excel to Logging Data Processing, Petroleum Instruments, 21 (2008), 2, pp. 58-60
PDF VERSION [DOWNLOAD]
A method for logging data reconstruction based on transfer learning

© 2026 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence