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
  • [1] Crop pest classification based on deep convolutional neural network and transfer learning
    Thenmozhi, K.
    Reddy, U. Srinivasulu
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2019, 164
  • [2] A chaotic two-dimensional image classification algorithm based on convolutional neural networks
    Zhou, Xuefang
    Wang, Hongliang
    Hu, Junchao
    Li, Haozhen
    Xu, Mengmeng
    Miao, Hu
    CHAOS SOLITONS & FRACTALS, 2025, 195
  • [3] Fire Detection based on a Two-Dimensional Convolutional Neural Network and Temporal Analysis
    de Venancio, Pedro Vinicius A. B.
    Rezende, Tamires M.
    Lisboa, Adriano C.
    Barbosa, Adriano V.
    2021 IEEE LATIN AMERICAN CONFERENCE ON COMPUTATIONAL INTELLIGENCE (LA-CCI), 2021,
  • [4] Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network
    Hasan, Md Mahibul
    Wang, Zhijie
    Hussain, Muhammad Ather Iqbal
    Fatima, Kaniz
    SENSORS, 2021, 21 (22)
  • [5] Hyperspectral image classification using convolutional neural network and two-dimensional complex Gabor transform
    Hanbay, Kazim
    JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, 2020, 35 (01): : 443 - 456
  • [6] Convolutional neural network: Deep learning-based classification of building quality problems
    Zhong, Botao
    Xing, Xuejiao
    Love, Peter
    Wang, Xu
    Luo, Hanbin
    ADVANCED ENGINEERING INFORMATICS, 2019, 40 : 46 - 57
  • [7] Deep Learning Model for Point Cloud Classification Based on Graph Convolutional Network
    Wang Xujiao
    Ma Jie
    Wang Nannan
    Ma Pengfei
    Yang Lichaung
    LASER & OPTOELECTRONICS PROGRESS, 2019, 56 (21)
  • [8] Vocal cord lesions classification based on deep convolutional neural network and transfer learning
    Zhao, Qian
    He, Yuqing
    Wu, Yanda
    Huang, Dongyan
    Wang, Yang
    Sun, Cai
    Ju, Jun
    Wang, Jiasen
    Jianshuo-li Mahr, Jeremy
    MEDICAL PHYSICS, 2022, 49 (01) : 432 - 442
  • [9] A New Deep Learning Model for the Classification of Poisonous and Edible Mushrooms Based on Improved AlexNet Convolutional Neural Network
    Ketwongsa, Wacharaphol
    Boonlue, Sophon
    Kokaew, Urachart
    APPLIED SCIENCES-BASEL, 2022, 12 (07):
  • [10] Rocket Image Classification Based on Deep Convolutional Neural Network
    Zhang, Liang
    Chen, Zhenhua
    Wang, Jian
    Huang, Zhaodun
    2018 10TH INTERNATIONAL CONFERENCE ON COMMUNICATIONS, CIRCUITS AND SYSTEMS (ICCCAS 2018), 2018, : 383 - 386