吉林大学学报(信息科学版) ›› 2022, Vol. 40 ›› Issue (1): 51-63.

• • 上一篇    下一篇

基于一维卷积神经网络的岩石物理相识别

李盼池, 李文杰   

  1. 东北石油大学 计算机与信息技术学院, 黑龙江 大庆 163318
  • 收稿日期:2021-07-13 出版日期:2022-01-25 发布日期:2022-01-27
  • 作者简介:李盼池(1969— ), 男, 河北大城人, 东北石油大学教授, 博士生导师, 主要从事量子机器学习、深度学习及其在资源信息工程中的应用研究,(Tel)86-13936853869(E-mail)lipanchi@vip.sina.com
  • 基金资助:
    黑龙江省优秀青年科学基金资助项目(YQ2020D001); 中国石油科技创新基金资助项目(2020D-5007-0102)

Identification of Petrophysical Facies Based on One-Dimensional Convolutional Neural Networks

LI Panchi, LI Wenjie   

  1. School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China
  • Received:2021-07-13 Online:2022-01-25 Published:2022-01-27

摘要: 为解决岩石物理相识别问题, 提出了一种基于可解释一维卷积神经网络的识别方法。 该方法通过引入全局平均池化层, 突出了测井曲线波形的动态变化部分; 并且通过分类激活映射增强了方法的可解释性; 通过引入扩张卷积和批量归一化, 弥补了由全局平均池化层引起的性能下降。 实验结果表明, 测试集中 4 种岩石物理相的平均 F1 分数为 0. 97, 相比其他同类方法提升了 0. 15 左右。 研究表明, 该方法可用于识别岩石物理相,并可提高分类过程中的可解释性, 从而为预测优质致密砂岩储层提供了一种新的深度学习方法。


关键词: 岩石物理相, 可解释一维卷积神经网络, 全局平均池化层, 扩张卷积, 批量归一化

Abstract: Aiming at the problem of rock physical facies identification, a identification method based on the interpretable one-dimensional convolutional neural network is proposed. By introducing the global average pooling layer, the dynamic variation part of the logging waveform is highlighted. The interpretability of the method is enhanced by the classification activation mapping. By introducing dilated convolution and batch normalization, the performance degradation caused by the global average pooling layer is compensated. According to the experimental results, the average F1 score of the four petrophysical facies in the test set is 0. 97, which is about 0. 15 higher than that of other similar methods. The results show that the proposed method can be used to identify petrophysical facies and improve the interpretability in the classification process, providing a new deep learning method for the prediction of high quality tight sandstone reservoirs.


Key words: petrophysical facies, interpretable one-dimensional convolutional neural networks, global average pooling layer, dilated convolution, batch normalization

中图分类号: 

  • TP391