Shale oil production predication based on an empirical modelconstrained CNN-LSTM  

作　　者：Qiang Zhou Zhengdong Lei Zhewei Chen Yuhan Wang Yishan Liu Zhenhua Xu Yuqi Liu 

机构地区：[1]Research Institute of Petroleum Exploration and Development,PetroChina,Beijing,100083,China [2]School of Energy Resources,China University of Geosciences,Beijing,100083,China

出　　处：《Energy Geoscience》2024年第2期232-239,共8页能源地球科学（英文）

基　　金：funded by the National Natural Science Foundation of China(No.51974356).

摘　　要：Accurately predicting the production rate and estimated ultimate recovery(EUR)of shale oil wells is vital for efficient shale oil development.Although numerical simulations provide accurate predictions,their high time,data,and labor demands call for a swifter,yet precise,method.This study introduces the DuongeCNNeLSTM(D-C-L)model,which integrates a convolutional neural network(CNN)with a long short-term memory(LSTM)network and is grounded on the empirical Duong model for physical constraints.Compared to traditional approaches,the D-C-L model demonstrates superior precision,efficiency,and cost-effectiveness in predicting shale oil production.

关 键 词：Shale oil Production prediction D-C-L Physical constraint 

分 类 号：P618.13[天文地球—矿床学]