Prediction of Low-Permeability Reservoirs Performances Using Long and Short-Term Memory Machine Learning
作者机构:School of GeosciencesYangtze UniversityWuhan430100China
出 版 物:《Fluid Dynamics & Materials Processing》 (流体力学与材料加工(英文))
年 卷 期:2022年第18卷第5期
页 面:1521-1528页
核心收录:
学科分类:0202[经济学-应用经济学] 02[经济学] 020205[经济学-产业经济学] 0805[工学-材料科学与工程(可授工学、理学学位)]
基 金:The authors received no specific funding for this study
主 题:Water flooding flow in porous media data-driven LSTM CFD
摘 要:In order to overcome the typical limitations of numerical simulation methods used to estimate the production of low-permeability reservoirs,in this study,a new data-driven approach is proposed for the case of water-driven hypo-permeable *** particular,given the bottlenecks of traditional recurrent neural networks in handling time series data,a neural network with long and short-term memory is used for such a *** method can reduce the time required to solve a large number of partial differential *** such,it can therefore significantly improve the efficiency in predicting the needed production *** examples about water-driven hypotonic reservoirs are provided to demonstrate the correctness of the method and its ability to meet the requirements for practical reservoir applications.