A robust deep structured prediction model for petroleum reservoir characterization using pressure transient test data

作     者：Rakesh Kumar Pandey Anil Kumar Ajay Mandal Rakesh Kumar Pandey;Anil Kumar;Ajay Mandal

作者机构：Department of Petroleum and Energy StudiesSchool of Engineering and TechnologyDIT UniversityDehradun248009India Data Science Research GroupSchool of ComputingDIT UniversityDehradun248009India Department of Petroleum EngineeringIndian Institute of Technology(Indian School of Mines)Dhanbad826004India 

出 版 物：《Petroleum Research》 (石油研究（英文）)

年 卷 期：2022年第7卷第2期

页      面：204-219页

核心收录：

学科分类：0709[理学-地质学] 0819[工学-矿业工程] 0808[工学-电气工程] 081803[工学-地质工程] 08[工学] 0708[理学-地球物理学] 0807[工学-动力工程及工程热物理] 0818[工学-地质资源与地质工程] 0816[工学-测绘科学与技术] 

基　　金：the Oil Industry Development Board,Ministry of Petroleum&Natural Gas,Government of India[Grant Number:4/3/2020-OIDB] and DIT University[Grant Num-ber:DITU/R&D/2021/4/Department of Petroleum and Energy Studies] 

主　　题：Well test Reservoir characterization Automatic interpretation Prediction model Hyperparameter tuning Performance indicator 

摘      要：A robust deep learning model consisting of long short-term memory and fully connected neural net-works has been proposed to automatically interpret homogeneous petroleum reservoirs having infinite,no flow,and constant pressure outer boundary *** pressure change data recorded during the well test operation along with its derivative is input into the model to perform the classification for identifying the reservoir model and,further,regression to estimate output *** noise was added to analytical models while generating the synthetic training *** hyperparameters were regulated to perform model optimization,resulting in a batch size of 64,Adam optimization algorithm,learning rate of 0.01,and 80:10:10 data split ratio as the best choices of *** perfor-mance accuracy also increased with an increase in the number of samples during *** classification and regression metrics have been used to evaluate the performance of the *** paper also demonstrates the prediction performance of the optimized model using simulated and actual oil well pressure drawdown test *** proposed model achieved minimum and maximum relative errors of 0.0019 and 0.0308,respectively,in estimating output for the simulated test cases and relative error of 0.0319 for the real test case.