Rock physics and machine learning comparison: elastic properties prediction and scale dependency

Rock physics diagnostics (RPD) established based upon the well data are used to deterministically predict elastic properties of rocks from measured petrophysical rock parameters. However, with the recent advances in statistical methods, machine learning (ML) can help to build a shortcut between raw...

Full description

Bibliographic Details
Main Authors: Vagif Suleymanov, Ammar El-Husseiny, Guenther Glatz, Jack Dvorkin
Format: Article
Language:English
Published: Frontiers Media S.A. 2023-06-01
Series:Frontiers in Earth Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/feart.2023.1095252/full
_version_ 1827932484411588608
author Vagif Suleymanov
Ammar El-Husseiny
Guenther Glatz
Jack Dvorkin
author_facet Vagif Suleymanov
Ammar El-Husseiny
Guenther Glatz
Jack Dvorkin
author_sort Vagif Suleymanov
collection DOAJ
description Rock physics diagnostics (RPD) established based upon the well data are used to deterministically predict elastic properties of rocks from measured petrophysical rock parameters. However, with the recent advances in statistical methods, machine learning (ML) can help to build a shortcut between raw well data and rock properties of interest. Several studies have reported the comparison of rock physics and machine learning methods for the prediction of rock properties, but the scale dependence of the ML models was never investigated. This study aims at comparing the results from rock physics and machine learning models for predicting elastic properties such as bulk density (ρb), P-wave velocity (Vp), S-wave velocity (Vs), as well as Poisson’s ratio (v) and acoustic impedance (Ip) in a well from the Gulf of Mexico (GOM) in two different scale scenarios: the well log and seismic scales. The well data under examination was split into training and testing subsets to optimize and test the developed ML models. The RPD approach was also used to validate and compare the accuracy of predicted elastic properties. Backus averaging was later applied to upscale the well data to the seismic scale to examine the scale dependence and prediction accuracy of aforementioned physics-driven and data-driven approaches. Results show that RPD and ML methods provided consistent results at both well log and seismic scales, suggesting the scale independence of both approaches. Moreover, ML models showed better estimation of rock properties due to their “apparent” match with measured data at both scales compared to the RPD approach where a significant mismatch between measured and predicted rock properties was found in the reservoir section of the well. However, by conducting further quality control of the sonic data, it was found that the measured Poisson’s ratio was extremely high in the gas-saturated interval. Hence, the prediction from ML models in this particular case cannot be trusted as ML models were trained based on poor-quality well data with non-realistic Vs and v values. Such an issue, however, could be identified and corrected using RPD as presented in this study. We demonstrate the importance of incorporating domain knowledge, i.e., rock physics, to check data quality and validate results from data-driven models.
first_indexed 2024-03-13T07:09:21Z
format Article
id doaj.art-19d1baf05f5644a1be0dba2cdb308876
institution Directory Open Access Journal
issn 2296-6463
language English
last_indexed 2024-03-13T07:09:21Z
publishDate 2023-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Earth Science
spelling doaj.art-19d1baf05f5644a1be0dba2cdb3088762023-06-06T04:32:37ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632023-06-011110.3389/feart.2023.10952521095252Rock physics and machine learning comparison: elastic properties prediction and scale dependencyVagif SuleymanovAmmar El-HusseinyGuenther GlatzJack DvorkinRock physics diagnostics (RPD) established based upon the well data are used to deterministically predict elastic properties of rocks from measured petrophysical rock parameters. However, with the recent advances in statistical methods, machine learning (ML) can help to build a shortcut between raw well data and rock properties of interest. Several studies have reported the comparison of rock physics and machine learning methods for the prediction of rock properties, but the scale dependence of the ML models was never investigated. This study aims at comparing the results from rock physics and machine learning models for predicting elastic properties such as bulk density (ρb), P-wave velocity (Vp), S-wave velocity (Vs), as well as Poisson’s ratio (v) and acoustic impedance (Ip) in a well from the Gulf of Mexico (GOM) in two different scale scenarios: the well log and seismic scales. The well data under examination was split into training and testing subsets to optimize and test the developed ML models. The RPD approach was also used to validate and compare the accuracy of predicted elastic properties. Backus averaging was later applied to upscale the well data to the seismic scale to examine the scale dependence and prediction accuracy of aforementioned physics-driven and data-driven approaches. Results show that RPD and ML methods provided consistent results at both well log and seismic scales, suggesting the scale independence of both approaches. Moreover, ML models showed better estimation of rock properties due to their “apparent” match with measured data at both scales compared to the RPD approach where a significant mismatch between measured and predicted rock properties was found in the reservoir section of the well. However, by conducting further quality control of the sonic data, it was found that the measured Poisson’s ratio was extremely high in the gas-saturated interval. Hence, the prediction from ML models in this particular case cannot be trusted as ML models were trained based on poor-quality well data with non-realistic Vs and v values. Such an issue, however, could be identified and corrected using RPD as presented in this study. We demonstrate the importance of incorporating domain knowledge, i.e., rock physics, to check data quality and validate results from data-driven models.https://www.frontiersin.org/articles/10.3389/feart.2023.1095252/fullrock physicsmachine learning (ML)seismic scalepetrophyisicselastic properities
spellingShingle Vagif Suleymanov
Ammar El-Husseiny
Guenther Glatz
Jack Dvorkin
Rock physics and machine learning comparison: elastic properties prediction and scale dependency
Frontiers in Earth Science
rock physics
machine learning (ML)
seismic scale
petrophyisics
elastic properities
title Rock physics and machine learning comparison: elastic properties prediction and scale dependency
title_full Rock physics and machine learning comparison: elastic properties prediction and scale dependency
title_fullStr Rock physics and machine learning comparison: elastic properties prediction and scale dependency
title_full_unstemmed Rock physics and machine learning comparison: elastic properties prediction and scale dependency
title_short Rock physics and machine learning comparison: elastic properties prediction and scale dependency
title_sort rock physics and machine learning comparison elastic properties prediction and scale dependency
topic rock physics
machine learning (ML)
seismic scale
petrophyisics
elastic properities
url https://www.frontiersin.org/articles/10.3389/feart.2023.1095252/full
work_keys_str_mv AT vagifsuleymanov rockphysicsandmachinelearningcomparisonelasticpropertiespredictionandscaledependency
AT ammarelhusseiny rockphysicsandmachinelearningcomparisonelasticpropertiespredictionandscaledependency
AT guentherglatz rockphysicsandmachinelearningcomparisonelasticpropertiespredictionandscaledependency
AT jackdvorkin rockphysicsandmachinelearningcomparisonelasticpropertiespredictionandscaledependency