基于多分辨率图谱聚类的测井岩性分析新方法

IF 2.1 3区 地球科学 Q3 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
{"title":"基于多分辨率图谱聚类的测井岩性分析新方法","authors":"","doi":"10.1007/s10596-024-10277-y","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>The lithofacies analysis of logging data is an essential step in reservoir evaluation. Multiresolution graph-based clustering (MRGC) is a commonly used methodology that provides information on the best number of clusters and cluster fitting results for geological understanding. However, the cluster fusion approach of MRGC often leads to an overemphasis of the boundary constraints among clusters. MRGC neglects the global cluster distribution relationship, which limits its practical application effectiveness. This paper proposes a new methodology, named kernel multiresolution graph-based clustering (KMRGC), to improve the merging part of clustering in MRGC, and it can give more weight to the spatial relationship characteristics among clusters. The clustering performance of K-means, Gaussian Mixture Model(GMM), fuzzy c-means(FCM), Density-Based Spatial Clustering of Applications with Noise(DBSCN), spectral clustering, MRGC and KMRGC algorithm was evaluated on a publicly available training set and noisy dataset, and the best results in terms of the adjusted Rand coefficients and normalized mutual information(NMI) coefficients on most of the datasets were obtained using KMRGC algorithm. Finally, KMRGC was used for logging data lithofacies clustering in cased wells, and the clustering effect of KMRGC algorithm was much better than that of the K-means, GMM, FCM, DBSCN, spectral clustering and MRGC algorithms, and the accuracy and stability were better.</p>","PeriodicalId":10662,"journal":{"name":"Computational Geosciences","volume":"162 1","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2024-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A new method based on multiresolution graph-based clustering for lithofacies analysis of well logging\",\"authors\":\"\",\"doi\":\"10.1007/s10596-024-10277-y\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<h3>Abstract</h3> <p>The lithofacies analysis of logging data is an essential step in reservoir evaluation. Multiresolution graph-based clustering (MRGC) is a commonly used methodology that provides information on the best number of clusters and cluster fitting results for geological understanding. However, the cluster fusion approach of MRGC often leads to an overemphasis of the boundary constraints among clusters. MRGC neglects the global cluster distribution relationship, which limits its practical application effectiveness. This paper proposes a new methodology, named kernel multiresolution graph-based clustering (KMRGC), to improve the merging part of clustering in MRGC, and it can give more weight to the spatial relationship characteristics among clusters. The clustering performance of K-means, Gaussian Mixture Model(GMM), fuzzy c-means(FCM), Density-Based Spatial Clustering of Applications with Noise(DBSCN), spectral clustering, MRGC and KMRGC algorithm was evaluated on a publicly available training set and noisy dataset, and the best results in terms of the adjusted Rand coefficients and normalized mutual information(NMI) coefficients on most of the datasets were obtained using KMRGC algorithm. Finally, KMRGC was used for logging data lithofacies clustering in cased wells, and the clustering effect of KMRGC algorithm was much better than that of the K-means, GMM, FCM, DBSCN, spectral clustering and MRGC algorithms, and the accuracy and stability were better.</p>\",\"PeriodicalId\":10662,\"journal\":{\"name\":\"Computational Geosciences\",\"volume\":\"162 1\",\"pages\":\"\"},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2024-03-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computational Geosciences\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1007/s10596-024-10277-y\",\"RegionNum\":3,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computational Geosciences","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1007/s10596-024-10277-y","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

摘要

摘要 测井数据的岩性分析是储层评价的重要步骤。基于多分辨率图的聚类(MRGC)是一种常用的方法,可提供最佳聚类数量和聚类拟合结果的信息,以帮助理解地质。然而,MRGC 的聚类融合方法往往会导致过分强调聚类之间的边界约束。MRGC 忽视了全局聚类分布关系,限制了其实际应用效果。本文提出了一种新的方法,即基于核多分辨率图的聚类(KMRGC),以改进 MRGC 中的聚类合并部分,并能更多地考虑聚类间的空间关系特征。在公开的训练集和噪声数据集上评估了 K-均值、高斯混合模型(GMM)、模糊 C-均值(FCM)、基于密度的噪声应用空间聚类(DBSCN)、光谱聚类、MRGC 和 KMRGC 算法的聚类性能、结果表明,在大多数数据集上,KMRGC 算法在调整后的 Rand 系数和归一化互信息(NMI)系数方面取得了最佳结果。最后,将 KMRGC 算法用于套管井测井数据岩性聚类,KMRGC 算法的聚类效果远优于 K-means、GMM、FCM、DBSCN、光谱聚类和 MRGC 算法,且准确性和稳定性更好。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A new method based on multiresolution graph-based clustering for lithofacies analysis of well logging

Abstract

The lithofacies analysis of logging data is an essential step in reservoir evaluation. Multiresolution graph-based clustering (MRGC) is a commonly used methodology that provides information on the best number of clusters and cluster fitting results for geological understanding. However, the cluster fusion approach of MRGC often leads to an overemphasis of the boundary constraints among clusters. MRGC neglects the global cluster distribution relationship, which limits its practical application effectiveness. This paper proposes a new methodology, named kernel multiresolution graph-based clustering (KMRGC), to improve the merging part of clustering in MRGC, and it can give more weight to the spatial relationship characteristics among clusters. The clustering performance of K-means, Gaussian Mixture Model(GMM), fuzzy c-means(FCM), Density-Based Spatial Clustering of Applications with Noise(DBSCN), spectral clustering, MRGC and KMRGC algorithm was evaluated on a publicly available training set and noisy dataset, and the best results in terms of the adjusted Rand coefficients and normalized mutual information(NMI) coefficients on most of the datasets were obtained using KMRGC algorithm. Finally, KMRGC was used for logging data lithofacies clustering in cased wells, and the clustering effect of KMRGC algorithm was much better than that of the K-means, GMM, FCM, DBSCN, spectral clustering and MRGC algorithms, and the accuracy and stability were better.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Computational Geosciences
Computational Geosciences 地学-地球科学综合
CiteScore
6.10
自引率
4.00%
发文量
63
审稿时长
6-12 weeks
期刊介绍: Computational Geosciences publishes high quality papers on mathematical modeling, simulation, numerical analysis, and other computational aspects of the geosciences. In particular the journal is focused on advanced numerical methods for the simulation of subsurface flow and transport, and associated aspects such as discretization, gridding, upscaling, optimization, data assimilation, uncertainty assessment, and high performance parallel and grid computing. Papers treating similar topics but with applications to other fields in the geosciences, such as geomechanics, geophysics, oceanography, or meteorology, will also be considered. The journal provides a platform for interaction and multidisciplinary collaboration among diverse scientific groups, from both academia and industry, which share an interest in developing mathematical models and efficient algorithms for solving them, such as mathematicians, engineers, chemists, physicists, and geoscientists.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信