Digital construction of geophysical well logging curves using the LSTM deep-learning network

被引:6
|
作者
Li, Jing [1 ]
Gao, Guozhong [1 ]
机构
[1] Yangtze Univ, Coll Geophys & Petr Resources, Wuhan, Peoples R China
关键词
well logging curves; LSTM; RNN; deep learning; digital well logging curve construction; PREDICTION; MODEL;
D O I
10.3389/feart.2022.1041807
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
A complete well logging suite is needed frequently, but it is either unavailable or has missing parts. The mudstone section is prone to wellbore collapse, which often causes distortion in well logs. In many cases, well logging curves are never measured, yet are needed for petrophysical or other analyses. Re-logging is expensive and difficult to achieve, while manual construction of the missing well logging curves is costly and low in accuracy. The rapid technical evolution of deep-learning algorithms makes it possible to realize the digital construction of missing well logging curves with high precision in an automated fashion. In this article, a workflow is proposed for the digital construction of well logging curves based on the long short-term memory (LSTM) network. The LSTM network is chosen because it has the advantage of avoiding the vanishing gradient problem that exists in traditional recurrent neural networks (RNNs). Additionally, it can process sequential data. When it is used in the construction of missing well logging curves, it not only considers the relationship between each logging curve but also the influence of the data from a previous depth on data at the following depth. This influence is validated by exercises constructing acoustic, neutron porosity, and resistivity logging curves using the LSTM network, which effectively achieves high-precision construction of these missing curves. These exercises show that the LSTM network is highly superior to the RNN in the digital construction of well logging curves, in terms of accuracy, efficiency, and reliability.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] SOME PROBLEMS OF DIGITAL RECORDING OF GEOPHYSICAL WELL LOGGING
    KNEBEL, S
    STEINBRE.D
    ZEITSCHRIFT FUR ANGEWANDTE GEOLOGIE, 1967, 13 (04): : 218 - &
  • [2] Construction of machine learning data set for geophysical logging inversion
    Shao RongBo
    Shi YanQing
    Zhou Jun
    Xiao LiZhi
    Liao GuangZhi
    Hou ShengLuan
    CHINESE JOURNAL OF GEOPHYSICS-CHINESE EDITION, 2023, 66 (07): : 3086 - 3101
  • [3] Determination of fracture toughness for deep well rock with geophysical logging data
    Jin, Y.
    Chen, M.
    Zhang, X.
    Yanshilixue Yu Gongcheng Xuebao/Chinese Journal of Rock Mechanics and Engineering, 2001, 20 (04): : 454 - 456
  • [4] Spatiotemporal Deep-Learning Model With Graph Convolutional Network for Well Logs Prediction
    Feng, Shuo
    Li, Xuegui
    Zeng, Fang
    Hu, Zhongrui
    Sun, Yuhang
    Wang, Zepeng
    Duan, Hanxu
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20
  • [5] Delineation of bed boundaries of array induction logging curves using deep learning
    Zhang Lei
    Wang Jian
    Jiao RuiLi
    Hao Chen
    Wang Xiu-Ming
    Ji You-Ming
    APPLIED GEOPHYSICS, 2021, 18 (01) : 45 - 53
  • [6] Detection of Pavement Maintenance Treatments using Deep-Learning Network
    Gao, Lu
    Yu, Yao
    Ren, Yi Hao
    Lu, Pan
    TRANSPORTATION RESEARCH RECORD, 2021, 2675 (09) : 1434 - 1443
  • [7] Delineation of bed boundaries of array induction logging curves using deep learning
    Zhang Lei
    Wang Jian
    Jiao RuiLi
    Hao Chen
    Wang Xiu-Ming
    Ji You-Ming
    Applied Geophysics, 2021, 18 : 45 - 53
  • [8] AUTOMATED DIGITAL ANALYSIS OF RENAL CORE BIOPSY SPECIMENS USING A DEEP-LEARNING ARTIFICIAL INTELLIGENCE NETWORK
    Fenstermaker, Michael
    Tomlins, Scott
    Morgan, Todd
    JOURNAL OF UROLOGY, 2018, 199 (04): : E360 - E360
  • [9] Event-Tree Based Sequence Mining Using LSTM Deep-Learning Model
    Abonyi, Janos
    Karoly, Richard
    Dorgo, Gyula
    COMPLEXITY, 2021, 2021
  • [10] Lithology Identification Method Based on Machine Learning and Geophysical Well Logging
    Chen, Sisi
    Yu, Hongyan
    Liu, Wenhui
    Wang, Xiaofeng
    Zhang, Dongdong
    Wang, Lei
    JOURNAL OF ENERGY ENGINEERING, 2025, 151 (01)