Open Access

ARTICLE

Prediction of Low-Permeability Reservoirs Performances Using Long and Short-Term Memory Machine Learning

Guowei Zhu^*, Kangliang Guo, Haoran Yang, Xinchen Gao, Shuangshuang Zhang

School of Geosciences, Yangtze University, Wuhan, 430100, China

* Corresponding Author: Guowei Zhu. Email:

(This article belongs to the Special Issue: Meshless, Mesh-Based and Mesh-Reduction Methods Based Analysis of Fluid Flow in Porous Media)

Fluid Dynamics & Materials Processing 2022, 18(5), 1521-1528. https://doi.org/10.32604/fdmp.2022.020942

Received 21 December 2021; Accepted 08 February 2022; Issue published 27 May 2022

Abstract

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 reservoirs. In 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 purpose. This method can reduce the time required to solve a large number of partial differential equations. As such, it can therefore significantly improve the efficiency in predicting the needed production performances. Practical 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.

---

Keywords

---