Seismic Bayesian evidential learning: Estimation and uncertainty quantification of sub-resolution reservoir properties

TL;DR

This paper introduces a Bayesian evidential learning framework for directly estimating sub-resolution reservoir properties from seismic data, enabling uncertainty quantification without solving high-dimensional inverse problems.

Contribution

The authors develop a novel Bayesian evidential learning approach that models the direct relation between seismic data and reservoir properties, incorporating non-linear statistical models and uncertainty quantification.

Findings

Effective estimation of reservoir net-to-gross and fluid saturations from synthetic data.

Demonstrated uncertainty quantification in real offshore seismic data.

Applicable to sub-resolution thin-sand reservoirs using 3D seismic data.

Abstract

We present a framework that enables estimation of low-dimensional sub-resolution reservoir properties directly from seismic data, without requiring the solution of a high dimensional seismic inverse problem. Our workflow is based on the Bayesian evidential learning approach and exploits learning the direct relation between seismic data and reservoir properties to efficiently estimate reservoir properties. The theoretical framework we develop allows incorporation of non-linear statistical models for seismic estimation problems. Uncertainty quantification is performed with Approximate Bayesian Computation. With the help of a synthetic example of estimation of reservoir net-to-gross and average fluid saturations in sub-resolution thin-sand reservoir, several nuances are foregrounded regarding the applicability of unsupervised and supervised learning methods for seismic estimation problems. Finally, we demonstrate the efficacy of our approach by estimating posterior uncertainty of reservoir net-to-gross in sub-resolution thin-sand reservoir from an offshore delta dataset using 3D pre-stack seismic data.