Machine-learning-based porosity estimation from multifrequency poststack seismic data

Abstract

Estimating porosity models via seismic data is challenging due to the low signal-to-noise ratio and insufficient resolution of the data. Although impedance inversion is often used in combination with well logs, to obtain subseismic scale porosity data, several problems must be addressed. Alternatively, we have proposed a machine learning-based workflow to convert seismic data into porosity models. A residual U-Net++ (ResUNet++)-based workflow is designed to take multiple poststack seismic volumes with different frequency bands as input and estimate a corresponding porosity model as output. This workflow is demonstrated in a 3D channelized reservoir to estimate the porosity model, and the R2 score of more than 0.9 is achieved for training and validation data. Moreover, a stress test is performed by adding noise to the seismic data to verify the expandability of applications, and the results find a robust estimation with 5% added noise. The additional two ResUNet++ are trained to only take the lowest or highest resolution seismic data as input to estimate the porosity model, but they exhibit underfitting and overfitting, respectively, supporting the importance of using multiscale seismic data for the porosity estimation problem. We mainly use experimental cases with simulated data. Therefore, scaling ResUNet++ for real data is needed in future research, such as considering coherent noise in seismic data, allowing uncertainty in petrophysical parameters, and expanding the size of ResUNet++ to the practical reservoir extent.