Forecasting Gas Well Classification Based on a Two-Dimensional Convolutional Neural Network Deep Learning Model

被引:2
作者
Zhao, Chunlan [1 ]
Jia, Ying [1 ,2 ]
Qu, Yao [3 ]
Zheng, Wenjuan [3 ]
Hou, Shaodan [3 ]
Wang, Bing [4 ]
机构
[1] State Key Lab Shale Oil & Gas Enrichment Mech & Ef, Beijing 100083, Peoples R China
[2] Sinopec, Explorat & Prod Res Inst, Beijing 102206, Peoples R China
[3] Southwest Petr Univ, Sch Sci, Chengdu 610500, Peoples R China
[4] Southwest Petr Univ, Sch Comp Sci, Chengdu 610500, Peoples R China
关键词
type of gas well; gas well development indicators; deep learning; two-dimensional convolutional neural network; multi-class prediction;
D O I
10.3390/pr12050878
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
In response to the limitations of existing evaluation methods for gas well types in tight sandstone gas reservoirs, characterized by low indicator dimensions and a reliance on traditional methods with low prediction accuracy, therefore, a novel approach based on a two-dimensional convolutional neural network (2D-CNN) is proposed for predicting gas well types. First, gas well features are hierarchically selected using variance filtering, correlation coefficients, and the XGBoost algorithm. Then, gas well types are determined via spectral clustering, with each gas well labeled accordingly. Finally, the selected features are inputted, and classification labels are outputted into the 2D-CNN, where convolutional layers extract features of gas well indicators, and the pooling layer, which, trained by the backpropagation of CNN, performs secondary dimensionality reduction. A 2D-CNN gas well classification prediction model is constructed, and the softmax function is employed to determine well classifications. This methodology is applied to a specific tight gas reservoir. The study findings indicate the following: (1) Via two rounds of feature selection using the new algorithm, the number of gas well indicator dimensions is reduced from 29 to 15, thereby reducing the computational complexity of the model. (2) Gas wells are categorized into high, medium, and low types, addressing a deep learning multi-class prediction problem. (3) The new method achieves an accuracy of 0.99 and a loss value of 0.03, outperforming BP neural networks, XGBoost, LightGBM, long short-term memory networks (LSTMs), and one-dimensional convolutional neural networks (1D-CNNs). Overall, this innovative approach demonstrates superior efficacy in predicting gas well types, which is particularly valuable for tight sandstone gas reservoirs.
引用
收藏
页数:19
相关论文
共 50 条
  • [31] Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network
    Lee, Jeong Hyun
    Joo, Ijin
    Kang, Tae Wook
    Paik, Yong Han
    Sinn, Dong Hyun
    Ha, Sang Yun
    Kim, Kyunga
    Choi, Choonghwan
    Lee, Gunwoo
    Yi, Jonghyon
    Bang, Won-Chul
    [J]. EUROPEAN RADIOLOGY, 2020, 30 (02) : 1264 - 1273
  • [32] Deep Learning-Based Classification of Korean Basal Cell Carcinoma Using Convolutional Neural Network
    Chung, Hyun Jung
    Kim, Yoon Jae
    Song, Howon
    Ahn, Sung Ku
    Kim, Hyunggun
    Hwang, Heon
    [J]. JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, 2019, 9 (01) : 195 - 201
  • [33] Deep learning-based classification of eye diseases using Convolutional Neural Network for OCT images
    Elkholy, Mohamed
    Marzouk, Marwa A.
    [J]. FRONTIERS IN COMPUTER SCIENCE, 2024, 5
  • [34] Major Depressive Disorder Classification Based on Different Convolutional Neural Network Models: Deep Learning Approach
    Uyulan, Caglar
    Erguzel, Turker Tekin
    Unubol, Huseyin
    Cebi, Merve
    Sayar, Gokben Hizli
    Nezhadasad, Mehdi
    Tarhan, Nevzat
    [J]. CLINICAL EEG AND NEUROSCIENCE, 2021, 52 (01) : 38 - 51
  • [35] A deep learning approach for atrial fibrillation signals classification based on convolutional and modified Elman neural network
    Wang, Jibin
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2020, 102 : 670 - 679
  • [36] Automatic Defect Classification for Infrared Thermography in CFRP based on Deep Learning Dense Convolutional Neural Network
    Liu, Guozeng
    Gao, Weicheng
    Liu, Wei
    Chen, Yijiao
    Wang, Tianlong
    Xie, Yongzhi
    Bai, Weiliang
    Li, Zijing
    [J]. JOURNAL OF NONDESTRUCTIVE EVALUATION, 2024, 43 (03)
  • [37] Wireless capsule endoscopy multiclass classification using three-dimensional deep convolutional neural network model
    Bordbar, Mehrdokht
    Helfroush, Mohammad Sadegh
    Danyali, Habibollah
    Ejtehadi, Fardad
    [J]. BIOMEDICAL ENGINEERING ONLINE, 2023, 22 (01)
  • [38] Wireless capsule endoscopy multiclass classification using three-dimensional deep convolutional neural network model
    Mehrdokht Bordbar
    Mohammad Sadegh Helfroush
    Habibollah Danyali
    Fardad Ejtehadi
    [J]. BioMedical Engineering OnLine, 22
  • [39] Deep learning with convolutional neural network in radiology
    Yasaka, Koichiro
    Akai, Hiroyuki
    Kunimatsu, Akira
    Kiryu, Shigeru
    Abe, Osamu
    [J]. JAPANESE JOURNAL OF RADIOLOGY, 2018, 36 (04) : 257 - 272
  • [40] Deep learning with convolutional neural network in radiology
    Koichiro Yasaka
    Hiroyuki Akai
    Akira Kunimatsu
    Shigeru Kiryu
    Osamu Abe
    [J]. Japanese Journal of Radiology, 2018, 36 : 257 - 272