Title: Application of 1D CNN-BiGRU hybrid neural network to identify reservoir rock types in sandstone reservoir

Authors: Xinhao Zhang; Xianguo Zhang; Huafeng Liu; Xiao Li; Wenyu Li

Addresses: School of Geosciences, China University of Petroleum (East China), Qingdao, Shandong, China ' State Key Laboratory of Deep Oil and Gas, China University of Petroleum (East China), Qingdao, Shandong, China; School of Geosciences, China University of Petroleum (East China), Qingdao, Shandong, China ' School of Geosciences, China University of Petroleum (East China), Qingdao, Shandong, China ' School of Geosciences, China University of Petroleum (East China), Qingdao, Shandong, China ' College of Earth Science and Engineering, Shandong University of Science and Technology, Qingdao, Shandong, China

Abstract: Differences in reservoir petrology and physical properties of reservoir rocks significantly impact oil and gas field development. Accurate classification of reservoir rock type (RRT) and intelligent logging identification are essential for locating high-quality reservoirs, geological modelling, and studying the remaining oil distribution. We introduce a method for the classification and prediction of reservoir rock types using core samples, conventional logging and deep learning methods. This method is the first to apply a hybrid structure of the one-dimensional convolutional neural network and bidirectional gated recurrent unit (1D CNN-BiGRU) to reservoir rock type identification. The hybrid model is compared with single 1D CNN, BiGRU, and random forest models. In the test dataset, this hybrid model achieved an accuracy of 82.5%, with F1 scores of 0.778, 0.779, and 0.827 for RRT1, RRT2, and RRT3, respectively. Its performance surpassed that of the other models. [Received: October 16, 2024; Accepted: February 20, 2025]

Keywords: reservoir rock type; RRT; hierarchical clustering; deep learning; hybrid model; convolutional neural network; CNN; gated neural network; well logs; core data; case study; sandstone reservoir.

DOI: 10.1504/IJOGCT.2026.151695

International Journal of Oil, Gas and Coal Technology, 2026 Vol.39 No.2, pp.131 - 156

Received: 05 Oct 2024
Accepted: 20 Feb 2025
Published online: 16 Feb 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article