About This Item

This article has been peer-reviewed and accepted for publication in a future issue of the AAPG Bulletin. This abstract and associated PDF document are based on the authors' accepted "as is" manuscript.

Editorial Policy for Ahead of Print


Cite This Item

Display Citation

Share This Item

The AAPG/Datapages Combined Publications Database

AAPG Bulletin

Visit Publisher's Website  

Ahead of Print Abstract

AAPG Bulletin, Preliminary version published online Ahead of Print 10 January 2022.

Copyright © 2022. The American Association of Petroleum Geologists. All rights reserved.

DOI:10.1306/11192121014

A hybrid deep learning network for tight and shale reservoir characterization using pressure and rate transient data

Hamzeh Alimohammadi, Hamid Rahmanifard, and Shengnan (Nancy) Chen

Department of Chemical and Petroleum Engineering, Schulich School of Engineering, University of Calgary, 2500 University Dr. NW, Calgary, T2N 1N4, Alberta, Canada

Ahead of Print Abstract

Pressure and rate transient analysis has been widely used to determine the properties of a reservoir, such as boundary types, permeability, and formation pressure. Typically, one analytical model must be selected first to interpret the transient data; however, it is very difficult to determine which model suits the reservoir conditions. In this study, a hybrid deep learning (DL) model is developed to offer an alternative approach to characterize the reservoir (i.e., reservoir shape, flow boundary type, and porosity system) using pressure and rate transient data interpretation in unconventional tight and shale reservoirs. A multivariate synthetic dataset of pressure and rate transients is firstly generated from the analytical solutions. Five DL architectures of recurrent, convolutional and hybrid recurrent-convolutional types are trained on a multivariate time-series of five features: pressure, pressure derivative, normalized rate, normalized cumulative production, and normalized integral derivative cumulative production. The performances of these architectures are compared, and the hybrid convolutional neural networks – long short-term memory (CNN-LSTM) leads to the highest performance with an accuracy of 0.98 on validation data. The performance of the optimum architecture is examined on transient data generated from reservoir simulations, and results demonstrate that the developed architecture can correctly characterize the reservoir with a accuracy of 98%. The applicability of the hybrid architecture on different length and resolution time-series is also tested. It is found that the short-time flow regimes of wellbore storage and initial transition do not affect the machine learning (ML) architecture's classification performance, and the boundary dominated flow is the main regime for classification of these types of resources.

Pay-Per-View Purchase Options

The article is available through a document delivery service. Explain these Purchase Options.

Protected Document: $10
Internal PDF Document: $14
Open PDF Document: $24

AAPG Member?

Please login with your Member username and password.

Members of AAPG receive access to the full AAPG Bulletin Archives as part of their membership. For more information, contact the AAPG Membership Department at [email protected].

Please cite this AAPG Bulletin Ahead of Print article as:

Hamzeh Alimohammadi, Hamid Rahmanifard, Shengnan (Nancy) Chen: A hybrid deep learning network for tight and shale reservoir characterization using pressure and rate transient data, (in press; preliminary version published online Ahead of Print 10 January 2022: AAPG Bulletin, DOI:10.1306/11192121014.

Close