Identifying payable cluster distributions for improved reservoir characterization: a robust unsupervised ML strategy for rock typing of depositional facies in heterogeneous rocks
文献类型：期刊论文
| 作者 | Ashraf, Umar2,3; Anees, Aqsa2,3; Zhang, Hucai3; Ali, Muhammad4; Thanh, Hung Vo1,5,6; Yuan, Yujie7,8 |
| 刊名 | GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES
 |
| 出版日期 | 2024-12-01 |
| 卷号 | 10期号:1页码:22 |
| 关键词 | Unsupervised ML algorithms SOM K-means clustering Payable clusters distribution DBSCAN SHAP |
| ISSN号 | 2363-8419 |
| DOI | 10.1007/s40948-024-00848-9 |
| 英文摘要 | The oil and gas industry relies on accurately predicting profitable clusters in subsurface formations for geophysical reservoir analysis. It is challenging to predict payable clusters in complicated geological settings like the Lower Indus Basin, Pakistan. In complex, high-dimensional heterogeneous geological settings, traditional statistical methods seldom provide correct results. Therefore, this paper introduces a robust unsupervised AI strategy designed to identify and classify profitable zones using self-organizing maps (SOM) and K-means clustering techniques. Results of SOM and K-means clustering provided the reservoir potentials of six depositional facies types (MBSD, DCSD, MBSMD, SSiCL, SMDFM, MBSh) based on cluster distributions. The depositional facies MBSD and DCSD exhibited high similarity and achieved a maximum effective porosity (PHIE) value of >= 15%, indicating good reservoir rock typing (RRT) features. The density-based spatial clustering of applications with noise (DBSCAN) showed minimum outliers through meta cluster attributes and confirmed the reliability of the generated cluster results. Shapley Additive Explanations (SHAP) model identified PHIE as the most significant parameter and was beneficial in identifying payable and non-payable clustering zones. Additionally, this strategy highlights the importance of unsupervised AI in managing profitable cluster distribution across various geological formations, going beyond simple reservoir characterization. Six depositional facies & six clusters are categorized to find payable gas-bearing facies via robust unsupervised ML strategy.SOM showed that MBSD, DCSD, and MBSMD depositional facies have PHIE >= 14% in LGF.K-means identified six rock types (Ex-RRT, G-RRT, F-RRT, T-RRT, U-RRT, & P-RRT).DBSCAN provided the reliability of clusters by identifying the least outliers.The SHAP model determined that PHIE and GR are the most influential factors. |
| 资助项目 | National Natural Science Foundation of China ; Directorate General of Petroleum Concessions (DGPC), Ministry of Petroleum, Pakistan |
| WOS研究方向 | Energy & Fuels ; Engineering ; Geology |
| 语种 | 英语 |
| WOS记录号 | WOS:001282915700001 |
| 出版者 | SPRINGER HEIDELBERG |
| 源URL | [http://119.78.100.198/handle/2S6PX9GI/42141]  |
| 专题 | 中科院武汉岩土力学所 |
| 通讯作者 | Ashraf, Umar; Anees, Aqsa |
| 作者单位 | 1.Middle East Univ, MEU Res Unit, Amman, Jordan 2.Yunnan Univ, Inst Int Rivers & Ecosecur, Kunming 650500, Peoples R China 3.Yunnan Univ, Inst Ecol Res & Pollut Control Plateau Lakes, Sch Ecol & Environm Sci, Kunming 650500, Yunnan, Peoples R China 4.Chinese Acad Sci, Inst Rock & Soil Mech, State Key Lab Geomech & Geotech Engn, Wuhan 430071, Peoples R China 5.Van Lang Univ, Inst Computat Sci & Artificial Intelligence, Lab Computat Mech, Ho Chi Minh City, Vietnam 6.Van Lang Univ, Fac Mech Elect & Comp Engn, Sch Technol, Ho Chi Minh City, Vietnam 7.Yunnan Univ, Sch Earth Sci, Kunming 650500, Yunnan, Peoples R China 8.Edith Cowan Univ, Sch Engn, Joondalup, WA 6027, Australia |
| 推荐引用方式 GB/T 7714 | Ashraf, Umar,Anees, Aqsa,Zhang, Hucai,et al. Identifying payable cluster distributions for improved reservoir characterization: a robust unsupervised ML strategy for rock typing of depositional facies in heterogeneous rocks[J]. GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES,2024,10(1):22. |
| APA | Ashraf, Umar,Anees, Aqsa,Zhang, Hucai,Ali, Muhammad,Thanh, Hung Vo,&Yuan, Yujie.(2024).Identifying payable cluster distributions for improved reservoir characterization: a robust unsupervised ML strategy for rock typing of depositional facies in heterogeneous rocks.GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES,10(1),22. |
| MLA | Ashraf, Umar,et al."Identifying payable cluster distributions for improved reservoir characterization: a robust unsupervised ML strategy for rock typing of depositional facies in heterogeneous rocks".GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES 10.1(2024):22. |
入库方式： OAI收割
来源：武汉岩土力学研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。