中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 武汉岩土力学研究所
  3. 中科院武汉岩土力学所
Optimizing seismic-based reservoir property prediction: a synthetic data-driven approach using convolutional neural networks and transfer learning with real data integration

文献类型：期刊论文

作者Ali, Muhammad4; He, Changxingyue1; Wei, Ning4; Jiang, Ren5; Zhu, Peimin2; Hao, Zhang2; Hussain, Wakeel2; Ashraf, Umar3
刊名ARTIFICIAL INTELLIGENCE REVIEW
出版日期2024-11-30
卷号58期号:1页码:27
关键词Optimizing reservoir property Convolutional neural network Transfer learning Synthetic seismic gathers Pseudo wells Rock physics model
ISSN号0269-2821
DOI10.1007/s10462-024-11030-8
英文摘要Reservoir characterization through seismic data analysis is essential for exploration and production in the petroleum industry. However, seismic-to-well tie discrepancies, limited availability of high-quality well data, and resolution constraints pose a reliability challenge. While previous studies offer valuable insights, they still struggle to achieve high-resolution predictions in a complex geologically environment given high reliance on well data. This study integrates synthetic data-driven techniques with real data, including convolutional neural networks (CNN) and transfer learning, to improve seismic reservoir characterization. We utilize nearby well statistics and a rock physics model (RPM) to simulate pseudo wells representing various geological scenarios. Synthetic seismic gathers are generated from these pseudo wells, which are based on RPM and local well control, to train the CNN. Transfer learning is then applied to adapt the CNN to better distinguish between real and synthetic data, enhancing reservoir predictions. A comparative analysis of P-impedance predictions from three methodologies: theory-driven Pre-Stack-Seismic-Inversion (TDSI), Deep-Neural-Network (DNN), and our CNN approach, showed that CNN achieved nearly 97% prediction accuracy with low error rates, compared to relatively lower prediction accuracy rates of DNN (86.2%) and TDSI (81.5%) with high error rates, according to robust metrics including R-square, RMSE, MSE, and MAE. These results indicate that CNN not only enhanced resolution but also closely aligned with well data and superior lateral continuity, even in blind well scenarios. This study effectively integrates synthetic data-driven techniques with CNNs and transfer learning to advance seismic reservoir property prediction, offering a robust solution to overcome limitations in traditional and DNN-based approaches.
资助项目China's National Key RD Program[2023YFB4104200] ; National Natural Science Foundation of China[72243011]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001367069900001
出版者SPRINGER
源URL[http://119.78.100.198/handle/2S6PX9GI/43287]  
专题中科院武汉岩土力学所
通讯作者Wei, Ning
作者单位1.Southwest Oil & Gas Field Co, Res Inst Explorat & Dev, Chengdu 610041, Peoples R China
2.China Univ Geosci, Inst Geophys & Geomat, Wuhan, Peoples R China
3.Yunnan Univ, Sch Ecol & Environm Sci, Kunming, Peoples R China
4.Chinese Acad Sci, Inst Rock & Soil Mech, State Key Lab Geomech & Geotech Engn, Wuhan 430071, Peoples R China
5.Petro China Co Ltd, Res Inst Petr Explorat & Dev, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Ali, Muhammad,He, Changxingyue,Wei, Ning,et al. Optimizing seismic-based reservoir property prediction: a synthetic data-driven approach using convolutional neural networks and transfer learning with real data integration[J]. ARTIFICIAL INTELLIGENCE REVIEW,2024,58(1):27.
APA Ali, Muhammad.,He, Changxingyue.,Wei, Ning.,Jiang, Ren.,Zhu, Peimin.,...&Ashraf, Umar.(2024).Optimizing seismic-based reservoir property prediction: a synthetic data-driven approach using convolutional neural networks and transfer learning with real data integration.ARTIFICIAL INTELLIGENCE REVIEW,58(1),27.
MLA Ali, Muhammad,et al."Optimizing seismic-based reservoir property prediction: a synthetic data-driven approach using convolutional neural networks and transfer learning with real data integration".ARTIFICIAL INTELLIGENCE REVIEW 58.1(2024):27.

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。