首页|Better use of experience from other reservoirs for accurate production forecasting by learn-to-learn method

Better use of experience from other reservoirs for accurate production forecasting by learn-to-learn method

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
  • 维普
To assess whether a development strategy will be profitable enough,production forecasting is a crucial and difficult step in the process.The development history of other reservoirs in the same class tends to be studied to make predictions accurate.However,the permeability field,well patterns,and development regime must all be similar for two reservoirs to be considered in the same class.This results in very few available experiences from other reservoirs even though there is a lot of historical information on numerous reservoirs because it is difficult to find such similar reservoirs.This paper proposes a learn-to-learn method,which can better utilize a vast amount of historical data from various reservoirs.Intui-tively,the proposed method first learns how to learn samples before directly learning rules in samples.Technically,by utilizing gradients from networks with independent parameters and copied structure in each class of reservoirs,the proposed network obtains the optimal shared initial parameters which are regarded as transferable information across different classes.Based on that,the network is able to predict future production indices for the target reservoir by only training with very limited samples collected from reservoirs in the same class.Two cases further demonstrate its superiority in accuracy to other widely-used network methods.

Production forecastingMultiple patternsFew-shot learningTransfer learning

Hao-Chen Wang、Kai Zhang、Nancy Chen、Wen-Sheng Zhou、Chen Liu、Ji-Fu Wang、Li-Ming Zhang、Zhi-Gang Yu、Shi-Ti Cui、Mei-Chun Yang

展开 >

China University of Petroleum(East China),66 Changjiang West Road,Qingdao West Coast New Area,Qingdao,266580,Shandong,China

Sinopec Matrix Co.,LTD,Qingdao,266000,Shandong,China

Qingdao University of Technology,Qingdao,266071,Shandong,China

University of Calgary,2500 University Dr NW,Calgary,T2N 1N4,Alberta,Canada

State Key Laboratory of Offshore Oil Exploitation,Beijing,100028,China

CNOOC Research Institute Ltd,Beijing,100028,China

CNPC Tarim Oilfield Branch Company,Korla,841000,Xinjiang,China

National Engineering Laboratory for Exploration and Development of Low-Permeability Oil and Gas Fields,Xi'an,710000,Shaanxi,China

展开 >

国家自然科学基金国家自然科学基金国家自然科学基金Major Scientific and Technological Projects of CNPCMajor Scientific and Technological Projects of CNOOCScience and Technology Support Plan for Youth Innovation of University in Shandong Province高等学校学科创新引智计划(111计划)

522740575207434051874335ZD2019-183-008CCL2022RCPS0397RSN2019KJH002B08028

2024

10.1016/j.petsci.2023.04.015

石油科学(英文版)
中国石油大学（北京）

石油科学(英文版)

EI
影响因子：0.88
ISSN：1672-5107
年,卷(期)：2024.21(1)
  • 32