Deep learning reservoir porosity prediction method based on a spatiotemporal convolution bi-directional long short-term memory neural network model

Abstract

A relationship exists between petrophysical logs and reservoir porosity; however, obtaining analytic solutions is challenging. In this study, we propose a novel method for porosity prediction, which is based on the construction of a new model, namely spatiotemporal convolutional bi-directional long short-term memory (SCBLSTM) network model, based on the convolutional neural network (CNN) and bi-directional long short-term memory (BLSTM) network. The spatial characteristics are extracted by the CNN, and the deep-seated temporal characteristics are extracted by the BLSTM network to ensure that the network model can express the spatiotemporal features of log data. The construction of the model mainly includes network model design, data preprocessing, sample training, and data prediction. After excavating the internal relationship between reservoir porosity and petrophysical logs by training the neural network, reservoir porosity can be predicted directly from petrophysical logs. The simulation verification of the model is performed using the actual logging data. The results show that the SCBLSTM network model can more effectively extract the intrinsic features of logging data and has higher prediction accuracy and stronger stability that other benchmark models. Additionally, the SCBLSTM network model is suitable for the prediction of reservoir physical parameters, which is the problem with multiple series data, thereby providing a new idea for the accurate prediction of reservoir physical parameters.