Seismic Prediction of Porosity in the Norne Field: Utilizing Support Vector Regression and Empirical Models Driven by Bayesian Linearized Inversion
This work aims to improve the characterization of petrophysical properties by accurately estimating subsurface porosity using seismic and well data. The study includes Bayesian Linearized Inversion to obtain elastic parameters (e.g., compressional e shear wave velocities and densities). This reduces...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/616 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This work aims to improve the characterization of petrophysical properties by accurately estimating subsurface porosity using seismic and well data. The study includes Bayesian Linearized Inversion to obtain elastic parameters (e.g., compressional e shear wave velocities and densities). This reduces processing uncertainty and provides a reliable substitute for the standard Amplitude versus Offset inversion method. Furthermore, incorporating sparse spike wavelets with Bayesian Linearized Inversion refines the inversion output, facilitating the extraction of petrophysical properties. Combined with log data from seventeen wells, these inverted parameters serve as inputs for two porosity prediction models: the empirical Han’s equation and a more adaptable Support Vector Regression model, the latter demonstrating superior precision in most cases due to its flexible fitting and calibration capabilities. Results from the Norne field in the North Sea confirm the approach’s viability, with the Support Vector Regression model achieving a significant Pearson correlation coefficient of 90% in porosity prediction, underscoring the potential of machine learning techniques in improving subsurface exploration results. |
|---|---|
| ISSN: | 2076-3417 |