Velocity-Porosity Supermodel: A Deep Neural Networks based concept

TL;DR

This paper introduces a deep learning-based supermodel that unifies multiple empirical velocity-porosity transforms, enabling accurate rock property estimation across diverse geological conditions without parameter tuning.

Contribution

It proposes a novel deep neural network framework to create a versatile velocity-porosity supermodel applicable to various lithologies, overcoming limitations of existing models.

Findings

Deep neural networks effectively combine multiple empirical transforms.

The supermodel performs well across different lithological conditions.

Results demonstrate potential for broad application in rock physics modeling.

Abstract

Rock physics models (RPMs) are used to estimate the elastic properties (e.g. velocity, moduli) from the rock properties (e.g. porosity, lithology, fluid saturation). However, the rock properties drastically vary for different geological conditions, and it is not easy to find a model that is applicable under all scenarios. There exist several empirical velocity-porosity transforms as well as first-principle-based models, however, each of these has its own limitations. It is not very straight-forward to choose the correct RPM, and templates exist, which are overlapped with the log data to decide on the correct model. In this work, we use deep machine learning and explore the concept of designing a supermodel that can be used for several different lithological conditions without any parameter tuning. In this paper, this test is restricted to only empirical velocity-porosity transforms, however, the future goal is to design a rock physics supermodel that can be used on a variety of rock properties. The goal of this paper to is to combine the advantages of several existing empirical velocity-porosity transforms under a single framework, and design a velocity-porosity supermodel (VPS) using artificial neural networks (ANN) based deep learning. Two test cases are used and based on the results presented in this paper, it is clear that deep neural networks can be a potential tool to develop a supermodel for lithological modeling and characterization.