Machine Learning-Based Prediction of Subsurface Elastic Properties Using Seismic and Well-Log Data

초록

The elastic properties of subsurface media, such as density and P- and S-wave velocity, are essential for understanding the mechanical behavior of the subsurface as they reflect its physical and structural characteristics. Accurate elastic properties are increasingly critical for safety assessment, geological risk analysis, and reservoir characterization in subsurface applications. However, current data acquisition methods present complementary limitations: well-log data provide high-resolution and accurate elastic properties but offers only localized information due to spatial constraints, while seismic data covers regional areas but has lower resolution and accuracy. To address these limitations, this study develops a machine learning (ML) framework that integrates seismic and well-log data to improve the prediction accuracy of subsurface elastic properties. This study introduces a novel approach that integrates ML with Gaussian processes (GP), which allows not only elastic property prediction but also quantification of predictive uncertainty. The proposed approach was validated using well-log and post-stack seismic data from the Volve dataset. Five ML models were trained to predict density and P- and S-wave velocities, with the long short-term memory+GP model achieving superior performance among all tested models. The 3-D prediction capabilities were further validated by applying the trained model to a 3-D seismic cube from the Volve field, successfully estimating 3-D elastic properties and quantifying prediction uncertainty. While the approach improves uncertainty assessment, it should be noted that uncertainty quantification is often limited in highly heterogeneous zones, as prediction reliability is inherently dataset-dependent.

키워드