Lessons for machine learning from the analysis of porosity-permeability transforms for carbonate reservoirs

Male, Frank; Duncan, Ian J.

doi:10.1016/j.petrol.2019.106825

Title: Lessons for machine learning from the analysis of porosity-permeability transforms for carbonate reservoirs

Full Record
Other Related Research

Authors:: Male, Frank; Duncan, Ian J.

Publication Date:: 2020-04-01

Sponsoring Org.:: USDOE

OSTI Identifier:: 1580539

Grant/Contract Number:: FE0024375

Resource Type:: Publisher's Accepted Manuscript

Journal Name:: Journal of Petroleum Science and Engineering

Additional Journal Information:: Journal Name: Journal of Petroleum Science and Engineering Journal Volume: 187 Journal Issue: C; Journal ID: ISSN 0920-4105

Publisher:: Elsevier

Country of Publication:: Netherlands

Language:: English

Citation Formats


                    Male, Frank, and Duncan, Ian J. Lessons for machine learning from the analysis of porosity-permeability transforms for carbonate reservoirs.  Netherlands: N. p., 2020. 
Web.  doi:10.1016/j.petrol.2019.106825.

Copy to clipboard


                    Male, Frank, & Duncan, Ian J. Lessons for machine learning from the analysis of porosity-permeability transforms for carbonate reservoirs.  Netherlands.  https://doi.org/10.1016/j.petrol.2019.106825

Copy to clipboard


                    Male, Frank, and Duncan, Ian J. Wed .  
"Lessons for machine learning from the analysis of porosity-permeability transforms for carbonate reservoirs".  Netherlands.  https://doi.org/10.1016/j.petrol.2019.106825.

Copy to clipboard


                    
@article{osti_1580539,

  title        = {Lessons for machine learning from the analysis of porosity-permeability transforms for carbonate reservoirs},

  author       = {Male, Frank and Duncan, Ian J.},

  abstractNote = {},

  doi          = {10.1016/j.petrol.2019.106825},

  journal      = {Journal of Petroleum Science and Engineering},

  number       = C,

  volume       = 187,

  place        = {Netherlands},

  year         = {2020},

  month        = {4}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (Publisher)

Publisher's Version of Record
https://doi.org/10.1016/j.petrol.2019.106825

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 12 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Lessons for machine learning from the analysis of porosity-permeability transforms for carbonate reservoirs

Journal Article Male, Frank ; Duncan, Ian J. - Journal of Petroleum Science and Engineering

Not provided.
https://doi.org/10.1016/j.petrol.2019.106825
Comparison of permeability predictions on cemented sandstones with physics-based and machine learning approaches

Journal Article Male, Frank ; Jensen, Jerry L. ; Lake, Larry W. - Journal of Natural Gas Science and Engineering

Permeability prediction has been an important problem since the time of Darcy. Most approaches to solve this problem have used either idealized physical models or empirical relations. In recent years, machine learning (ML) has led to more accurate and robust, but less interpretable empirical models. Using 211 core samples collected from 12 wells in the Garn Sandstone from the North Sea, this study compared idealized physical models based on the Carman-Kozeny equation to interpretable ML models. We found that ML models trained on estimates of physical properties are more accurate than physical models. The results show evidence of a thresholdmore »« less
Cited by 18
https://doi.org/10.1016/j.jngse.2020.103244

Full Text Available
Secondary porosity prediction in complex carbonate reefs using 3D CT scan image analysis and machine learning

Journal Article Haagsma, Autumn ; Scharenberg, Mackenzie ; Keister, Laura ; ... - Journal of Petroleum Science and Engineering
https://doi.org/10.1016/j.petrol.2021.109087
Calibration of NMR porosity to estimate permeability in carbonate reservoirs

Journal Article Mason, Harris E ; Smith, Megan M ; Carroll, Susan A - International Journal of Greenhouse Gas Control

Considering the performance of carbon dioxide (CO₂) stored in geologic reservoirs requires some knowledge of the subsurface heterogeneity, where the most reliable data is extracted from wellbore measurements. This benefit is especially true for carbonate reservoirs were reactions between supercritical CO₂, the reservoir brine, and carbonate minerals create new storage capacity and enhanced permeability. Techniques like NMR well logging hold promise for estimating subsurface permeability, because the total porosity and pore size can be calculated from response of ¹H NMR signal. Resulting depth profiles of porosity and permeability from downhole logs are useful input for reservoir simulations and can bemore »« less
Cited by 6
https://doi.org/10.1016/j.ijggc.2019.05.008

Full Text Available
Regional-scale porosity and permeability variations in Upper Devonian Leduc buildups: Implications for reservoir development and prediction in carbonates

Journal Article Amthor, J E ; Mountjoy, E W ; Machel, H G - AAPG Bulletin

Upper Devonian carbonate rocks of the Rimbey-Meadowbrook reef trend in the subsurface of central Alberta are characterized by a wide range of porosity and permeability values. Dolostones show the highest values of absolute and average horizontal and vertical permeability. For all rock types, horizontal permeability averages tens of times to several hundred times the vertical permeability. If considered irrespective of burial depth, limestones and dolomitic limestones are more porous than dolostones. There is an overall decrease of porosity and permeability in Leduc Formation carbonates with increasing burial depth and thermal maturity along the reef trend. At relatively shallow burial depthsmore »« less

Similar Records