Petrophysical rock properties prediction from elastic properties using artificial neural network (ANN)

V. Suleymanov; A. El-Husseiny; J. Dvorkin

doi:10.3997/2214-4609.2022617015

Petrophysical rock properties prediction from elastic properties using artificial neural network (ANN)

V. Suleymanov, A. El-Husseiny, J. Dvorkin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The interpretation of elastic rock properties into petrophysical properties is usually performed using deterministic rock physics and statistics-based approaches at the seismic scale. In this study, a machine learning workflow has been developed for predicting petrophysical rock properties such as porosity, mineralogy, and pore fluid from measured elastic properties in the well. In particular, the bulk density, P- and S-wave velocity logs were used as inputs to predict the rock properties. The workflow shows promising results in predicting, porosity, clay content, and water saturation with high accuracy.

Original language	English
Title of host publication	6th EAGE Rock Physics Workshop
Publisher	European Association of Geoscientists and Engineers, EAGE
ISBN (Electronic)	9789462824515
DOIs	https://doi.org/10.3997/2214-4609.2022617015
State	Published - 2022
Event	6th EAGE Rock Physics Workshop 2022 - Riyadh, Saudi Arabia Duration: 15 Nov 2022 → 17 Nov 2022

Publication series

Name	6th EAGE Rock Physics Workshop

Conference

Conference	6th EAGE Rock Physics Workshop 2022
Country/Territory	Saudi Arabia
City	Riyadh
Period	15/11/22 → 17/11/22

Bibliographical note

Publisher Copyright:
© 6th EAGE Rock Physics Workshop 2022.

ASJC Scopus subject areas

Geotechnical Engineering and Engineering Geology

Access to Document

10.3997/2214-4609.2022617015

Cite this

@inproceedings{b5d063a84cef494fb6d6f60b7a589ee3,

title = "Petrophysical rock properties prediction from elastic properties using artificial neural network (ANN)",

abstract = "The interpretation of elastic rock properties into petrophysical properties is usually performed using deterministic rock physics and statistics-based approaches at the seismic scale. In this study, a machine learning workflow has been developed for predicting petrophysical rock properties such as porosity, mineralogy, and pore fluid from measured elastic properties in the well. In particular, the bulk density, P- and S-wave velocity logs were used as inputs to predict the rock properties. The workflow shows promising results in predicting, porosity, clay content, and water saturation with high accuracy.",

author = "V. Suleymanov and A. El-Husseiny and J. Dvorkin",

note = "Publisher Copyright: {\textcopyright} 6th EAGE Rock Physics Workshop 2022.; 6th EAGE Rock Physics Workshop 2022 ; Conference date: 15-11-2022 Through 17-11-2022",

year = "2022",

doi = "10.3997/2214-4609.2022617015",

language = "English",

series = "6th EAGE Rock Physics Workshop",

publisher = "European Association of Geoscientists and Engineers, EAGE",

booktitle = "6th EAGE Rock Physics Workshop",

}

Suleymanov, V, El-Husseiny, A & Dvorkin, J 2022, Petrophysical rock properties prediction from elastic properties using artificial neural network (ANN). in 6th EAGE Rock Physics Workshop. 6th EAGE Rock Physics Workshop, European Association of Geoscientists and Engineers, EAGE, 6th EAGE Rock Physics Workshop 2022, Riyadh, Saudi Arabia, 15/11/22. https://doi.org/10.3997/2214-4609.2022617015

Petrophysical rock properties prediction from elastic properties using artificial neural network (ANN). / Suleymanov, V.; El-Husseiny, A.; Dvorkin, J.
6th EAGE Rock Physics Workshop. European Association of Geoscientists and Engineers, EAGE, 2022. (6th EAGE Rock Physics Workshop).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Petrophysical rock properties prediction from elastic properties using artificial neural network (ANN)

AU - Suleymanov, V.

AU - El-Husseiny, A.

AU - Dvorkin, J.

PY - 2022

Y1 - 2022

N2 - The interpretation of elastic rock properties into petrophysical properties is usually performed using deterministic rock physics and statistics-based approaches at the seismic scale. In this study, a machine learning workflow has been developed for predicting petrophysical rock properties such as porosity, mineralogy, and pore fluid from measured elastic properties in the well. In particular, the bulk density, P- and S-wave velocity logs were used as inputs to predict the rock properties. The workflow shows promising results in predicting, porosity, clay content, and water saturation with high accuracy.

AB - The interpretation of elastic rock properties into petrophysical properties is usually performed using deterministic rock physics and statistics-based approaches at the seismic scale. In this study, a machine learning workflow has been developed for predicting petrophysical rock properties such as porosity, mineralogy, and pore fluid from measured elastic properties in the well. In particular, the bulk density, P- and S-wave velocity logs were used as inputs to predict the rock properties. The workflow shows promising results in predicting, porosity, clay content, and water saturation with high accuracy.

UR - https://www.scopus.com/pages/publications/85210843545

U2 - 10.3997/2214-4609.2022617015

DO - 10.3997/2214-4609.2022617015

M3 - Conference contribution

AN - SCOPUS:85210843545

T3 - 6th EAGE Rock Physics Workshop

BT - 6th EAGE Rock Physics Workshop

PB - European Association of Geoscientists and Engineers, EAGE

T2 - 6th EAGE Rock Physics Workshop 2022

Y2 - 15 November 2022 through 17 November 2022

ER -

Petrophysical rock properties prediction from elastic properties using artificial neural network (ANN)

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this