Porosity and permeability prediction using a transformer and periodic long short-term network

Abstract

Effective reservoir parameter prediction is important for subsurface characterization and understanding the fluid migration. However, conventional methods for obtaining porosity and permeability are based on either core measurements or mathematical/petrophysical modeling, which are expensive or inefficient. In this study, we propose a reliable and low-cost deep learning (DL) framework for reservoir permeability and porosity prediction from real logging data at different regions. We leverage an advanced learning architecture (i.e., the transformer model) and design a new regression network (RPTransformer) that is sensitive to the depth period change of the logging data. The RPTransformer is composed of 1-D convolutional, long- and short-term memory (LSTM), and transformer layers. First, we use a 1-D convolutional layer for the first layer of the network to extract the significant features from logging data. Then, the nonlinear mapping relationships between logging data and reservoir parameters are established using several LSTM layers with a period parameter. Afterward, we use the encoder in the vision transformer (ViT) with the self-attention mechanism to further extract logging data features. The proposed network is a data-driven supervised learning framework and shows highly accurate and robust prediction results when applied to different geographic regions. To demonstrate the reliable prediction performance of our proposed network, we compare it with several classic machine learning and state-of-the-art DL methods, e.g., random forest (RF), multilayer LSTM (MLSTM), and LSTNet. More importantly, we show the generalization and uncertainty of the network in real-world applications through comprehensive numerical experiments.

Hierarchical automated machine learning (AutoML) for advanced unconventional reservoir characterization

“…The approach could reduce errors when limited data is available and different log depths are present. Recently, a study by Yang 11 utilized state-of-the-art deep learning transformer model to predict porosity and achieved high accuracy. Several works have also extended the application of machine learning to conduct permeability predictions in both siliciclastic and carbonate reservoirs 12 , 13 .…”

Real-Time Prediction of Petrophysical Properties Using Machine Learning Based on Drilling Parameters

“…Machine learning (ML) algorithms offer promising solutions for different problems by analyzing vast amounts of data and identifying complex patterns and relationships that may not be apparent to human analysts. − By training the models on a data set that includes both input parameters and corresponding output measurements, the algorithms can learn the underlying patterns and create predictive models capable of estimating formation properties. Different authors discussed the application of machine learning in predicting formation porosity and permeability. − …”

Shear wave velocity prediction based on 1DCNN-BiLSTM network with attention mechanism

“…Although three gate control units are introduced in the LSTM network for information selection and memory, the above-mentioned problems still appear when directly using the LSTM network for S-wave velocity prediction as the logging depth becomes increasingly larger and the logging curve contains significantly more information. Many studies have attempted to incorporate attention mechanisms into various networks to help capture the global dependencies of data, e.g., the main ingredient of the Transformer is a self-attention block, and the Transformer has been successfully applied in the geophysical field (Harsuko and Alkhalifah, 2022;Yang et al, 2023).…”