Progress and Prospect for Machine Learning Applied in NMR Logging

Low-field nuclear magnetic resonance (NMR) technology has been widely used in petroleum engineering, which plays a critical role in reservoir evaluation and production prediction. However, the extremely weak signal and low signal-to-noise ratio (SNR) of low-field NMR leads to overlapping signals in...

Full description

Saved in:
Bibliographic Details
Main Authors: LUO Gang, LUO Sihui, XIAO Lizhi, FU Shaoqing, ZHANG Jiawei, SHAO Rongbo
Format: Article
Language:zho
Published: Editorial Office of Well Logging Technology 2023-12-01
Series:Cejing jishu
Subjects:
Online Access:https://www.cnpcwlt.com/#/digest?ArticleID=5537
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849328191950290944
author LUO Gang
LUO Sihui
XIAO Lizhi
FU Shaoqing
ZHANG Jiawei
SHAO Rongbo
author_facet LUO Gang
LUO Sihui
XIAO Lizhi
FU Shaoqing
ZHANG Jiawei
SHAO Rongbo
author_sort LUO Gang
collection DOAJ
description Low-field nuclear magnetic resonance (NMR) technology has been widely used in petroleum engineering, which plays a critical role in reservoir evaluation and production prediction. However, the extremely weak signal and low signal-to-noise ratio (SNR) of low-field NMR leads to overlapping signals in the NMR relaxation spectra and difficulties in the quantitative evaluation of fluid components. Therefore, it is very important to develop novel and practical NMR data processing methods to improve the application effects of NMR logging technology. With the rapid development of artificial intelligence technology, many scholars have proposed machine learning methods to improve the industry’s productivity. Firstly, this paper summarized the application and development of machine learning used in NMR logging. Secondly, the progress of machine learning methods applied in NMR logging data processing are analyzed, which are divided into three aspects including SNR enhancement, spectra resolution improvement, and quantitative fluid identification improvement. Finally, the future development of machine learning applied NMR logging data processing is summarized and recommended.
format Article
id doaj-art-27a40e4af9bc4a1ea73efc1047373a60
institution Kabale University
issn 1004-1338
language zho
publishDate 2023-12-01
publisher Editorial Office of Well Logging Technology
record_format Article
series Cejing jishu
spelling doaj-art-27a40e4af9bc4a1ea73efc1047373a602025-08-20T03:47:40ZzhoEditorial Office of Well Logging TechnologyCejing jishu1004-13382023-12-0147664365210.16489/j.issn.1004-1338.2023.06.0011004-1338(2023)06-0643-10Progress and Prospect for Machine Learning Applied in NMR LoggingLUO Gang0LUO Sihui1XIAO Lizhi2FU Shaoqing3ZHANG Jiawei4SHAO Rongbo5National Key Laboratory of Oil and Gas Resources and Engineering, China University of Petroleum (Beijing), Beijing 102249, ChinaNational Key Laboratory of Oil and Gas Resources and Engineering, China University of Petroleum (Beijing), Beijing 102249, ChinaNational Key Laboratory of Oil and Gas Resources and Engineering, China University of Petroleum (Beijing), Beijing 102249, ChinaWell Logging Technology Institute, China National Logging Corporation, Beijing 102206, ChinaNational Key Laboratory of Oil and Gas Resources and Engineering, China University of Petroleum (Beijing), Beijing 102249, ChinaNational Key Laboratory of Oil and Gas Resources and Engineering, China University of Petroleum (Beijing), Beijing 102249, ChinaLow-field nuclear magnetic resonance (NMR) technology has been widely used in petroleum engineering, which plays a critical role in reservoir evaluation and production prediction. However, the extremely weak signal and low signal-to-noise ratio (SNR) of low-field NMR leads to overlapping signals in the NMR relaxation spectra and difficulties in the quantitative evaluation of fluid components. Therefore, it is very important to develop novel and practical NMR data processing methods to improve the application effects of NMR logging technology. With the rapid development of artificial intelligence technology, many scholars have proposed machine learning methods to improve the industry’s productivity. Firstly, this paper summarized the application and development of machine learning used in NMR logging. Secondly, the progress of machine learning methods applied in NMR logging data processing are analyzed, which are divided into three aspects including SNR enhancement, spectra resolution improvement, and quantitative fluid identification improvement. Finally, the future development of machine learning applied NMR logging data processing is summarized and recommended.https://www.cnpcwlt.com/#/digest?ArticleID=5537nuclear magnetic resonance loggingmachine learningdeep learningdata processinginterpretation and application
spellingShingle LUO Gang
LUO Sihui
XIAO Lizhi
FU Shaoqing
ZHANG Jiawei
SHAO Rongbo
Progress and Prospect for Machine Learning Applied in NMR Logging
Cejing jishu
nuclear magnetic resonance logging
machine learning
deep learning
data processing
interpretation and application
title Progress and Prospect for Machine Learning Applied in NMR Logging
title_full Progress and Prospect for Machine Learning Applied in NMR Logging
title_fullStr Progress and Prospect for Machine Learning Applied in NMR Logging
title_full_unstemmed Progress and Prospect for Machine Learning Applied in NMR Logging
title_short Progress and Prospect for Machine Learning Applied in NMR Logging
title_sort progress and prospect for machine learning applied in nmr logging
topic nuclear magnetic resonance logging
machine learning
deep learning
data processing
interpretation and application
url https://www.cnpcwlt.com/#/digest?ArticleID=5537
work_keys_str_mv AT luogang progressandprospectformachinelearningappliedinnmrlogging
AT luosihui progressandprospectformachinelearningappliedinnmrlogging
AT xiaolizhi progressandprospectformachinelearningappliedinnmrlogging
AT fushaoqing progressandprospectformachinelearningappliedinnmrlogging
AT zhangjiawei progressandprospectformachinelearningappliedinnmrlogging
AT shaorongbo progressandprospectformachinelearningappliedinnmrlogging