Well-Logging Prediction Based on Hybrid Neural Network Model

被引:21
|
作者
Wu, Lei [1 ]
Dong, Zhenzhen [1 ]
Li, Weirong [1 ]
Jing, Cheng [1 ]
Qu, Bochao [1 ]
机构
[1] Xian Shiyou Univ, Petr Engn Dept, Xian 710065, Peoples R China
关键词
well-logging; convolutional neural network; long short-term memory; particle swarm optimization; hybrid model; deep learning;
D O I
10.3390/en14248583
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Well-logging is an important formation characterization and resource evaluation method in oil and gas exploration and development. However, there has been a shortage of well-logging data because Well-logging can only be measured by expensive and time-consuming field tests. In this study, we aimed to find effective machine learning techniques for well-logging data prediction, considering the temporal and spatial characteristics of well-logging data. To achieve this goal, the convolutional neural network (CNN) and the long short-term memory (LSTM) neural networks were combined to extract the spatial and temporal features of well-logging data, and the particle swarm optimization (PSO) algorithm was used to determine hyperparameters of the optimal CNN-LSTM architecture to predict logging curves in this study. We applied the proposed CNN-LSTM-PSO model, along with support vector regression, gradient-boosting regression, CNN-PSO, and LSTM-PSO models, to forecast photoelectric effect (PE) logs from other logs of the target well, and from logs of adjacent wells. Among the applied algorithms, the proposed CNN-LSTM-PSO model generated the best prediction of PE logs because it fully considers the spatio-temporal information of other well-logging curves. The prediction accuracy of the PE log using logs of the adjacent wells was not as good as that using the other well-logging data of the target well itself, due to geological uncertainties between the target well and adjacent wells. The results also show that the prediction accuracy of the models can be significantly improved with the PSO algorithm. The proposed CNN-LSTM-PSO model was found to enable reliable and efficient Well-logging prediction for existing and new drilled wells; further, as the reservoir complexity increases, the proxy model should be able to reduce the optimization time dramatically.
引用
收藏
页数:19
相关论文
共 50 条
  • [31] Petrophysical software for interpreting integrated well-logging data based on spectrometric gamma-logging
    D. V. Korost
    G. A. Kalmykov
    E. V. Reshetov
    V. S. Belokhin
    Moscow University Geology Bulletin, 2009, 64 (2) : 130 - 137
  • [32] Shale volume estimation based on the factor analysis of well-logging data
    Norbert P. Szabó
    Acta Geophysica, 2011, 59 : 935 - 953
  • [33] Inversion of time-dependent nuclear well-logging data using neural networks
    Carmine, Laura
    Aristodemou, Elsa
    Pain, Christopher
    Muggeridge, Ann
    de Oliveira, Cassiano
    GEOPHYSICAL PROSPECTING, 2008, 56 (01) : 115 - 140
  • [34] Detection imaging of impulse borehole well-logging radar
    Longfei Dang
    Hongchun Yang
    Baohua Teng
    EURASIP Journal on Image and Video Processing, 2018
  • [35] Prediction model of a hybrid recurrent neural network based on sequence decomposition
    Zhao, Jia
    Li, Changxiang
    Han, Longzhe
    Wu, Yannian
    Wu, Lieyang
    INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS, 2023, 18 (03) : 286 - 298
  • [36] Neural network based hybrid computing model for wind speed prediction
    Sheela, K. Gnana
    Deepa, S. N.
    NEUROCOMPUTING, 2013, 122 : 425 - 429
  • [37] Hybrid Prediction Model Based on BP Neural Network for Lung Cancer
    Sun, Aobing
    Tan, Yubo
    Zhang, Dexian
    2008 IEEE INTERNATIONAL SYMPOSIUM ON IT IN MEDICINE AND EDUCATION, VOLS 1 AND 2, PROCEEDINGS, 2008, : 532 - 535
  • [38] Hybrid prediction model of building energy consumption based on neural network
    Yu J.-Q.
    Yang S.-Y.
    Zhao A.-J.
    Gao Z.-K.
    Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2022, 56 (06): : 1220 - 1231
  • [39] Highway subsidence prediction based on neural network and hyperbolic hybrid model
    Liu, Wenhao
    Li, Xi
    Hu, Wusheng
    Dongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Southeast University (Natural Science Edition), 2013, 43 (SUPPL.2): : 380 - 383
  • [40] MULTIPLE PARAMETERS IDENTIFICATION PROBLEMS IN RESISTIVITY WELL-LOGGING
    CAI ZHIJIE *
    ChineseAnnalsofMathematics, 1998, (03) : 18 - 25