This study proposed a deep-learning-based approach that generates synthetic high-resolution log data from original-resolution log data for accurate reservoir characterization, where the resolution of the synthetic data is comparable to that of core data. The reliability of the proposed approach was tested with application to the Volve oil field in Norway using three deep-learning algorithms (i.e., deep neural network, convolutional neural network, and long short-term memory). These deep-learning algorithms were employed to generate high-resolution sonic log data from other log-type data. The overall performance of each algorithm was acceptable. In particular, the long short-term memory algorithm yields a coefficient of determination greater than 0.9 when the high-to-original-resolution ratios are two, five, and ten. We anticipate that the proposed model can be used to derive logging-based reservoir parameters with a resolution that is comparable to that of core-based reservoir parameters.
This study proposes a deep-learning-based model to generate synthetic compressional wave velocity (Vp) from well-logging data with application to the Ulleung Basin Gas Hydrate (UBGH) in the East Sea, Republic of Korea. Because a bottom-simulating reflector (BSR) is a key indicator to define the presence of gas hydrate, this study generates the Vp for identifying the BSR by detecting the morphology of the hydrate in terms of the change in acoustic velocity. Conventional easy-to-acquire logging parameters, such as gamma-ray, neutron porosity, bulk density, and photoelectric absorption, were selected as model inputs based on a sensitivity analysis. Long short-term memory (LSTM) and an artificial neural network (ANN) were used to design an efficient learning-based predictive model with sensitivity analysis for hyperparameters. The LSTM model outperforms the ANN model by preserving the geological sequence of the well-logging data. Ten-fold cross-validation was conducted to verify the consistency of the LSTM model and yielded satisfactory results, with an average coefficient of determination greater than 0.8. These numerical results imply that generating synthetic well-logging via deep learning can accurately estimate missing well-logging data, contributing to the reservoir characterization of gas-hydrate-bearing sediments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.