The SMART Initiative: Applying Machine Learning to Enable Efficient and Effective Real-Time Decisions for Geological Carbon Storage Operations

Grant Bromhal; Srikanta Mishra; George Guthrie; Fred Aminzadeh; Dustin Crandall; David Alumbaugh; Joshua White; Sherilyn Williams-Stroud; Nicholas Azzolina; Catherine Yonkofski; Tom McGuire; Rajesh Pawar; Jared Schuetter; Joseph Morris; Shane Butler; Hari Viswanathan; Tim Carr

doi:10.2139/ssrn.4296267

The SMART Initiative: Applying Machine Learning to Enable Efficient and Effective Real-Time Decisions for Geological Carbon Storage Operations

Grant Bromhal, Srikanta Mishra, George Guthrie, Fred Aminzadeh, Dustin Crandall, David Alumbaugh, Joshua White, Sherilyn Williams-Stroud, Nicholas Azzolina, Catherine Yonkofski, Tom McGuire, Rajesh Pawar, Jared Schuetter, Joseph Morris, Shane Butler, Hari Viswanathan, Tim Carr

Illinois State Geological Survey

Research output: Working paper › Preprint

Abstract

This paper provides an overview of the SMART Initiative – Science-Informed Machine Learning for Accelerating Real-Time Decisions in Subsurface Applications – that seeks to transform our interactions within and understanding of the subsurface, and significantly improve efficiency and effectiveness of field-scale carbon storage and unconventional oil and gas operations. The accomplishments of the recently concluded “proof-of-concept” Phase 1 are described. Goals for the “field deployement” of ML-assisted tools and workflows for both greenfield (i.e., pre-injection permitting) and brownfield (i.e., active injection operational control and post-injection site care) applications in Phase 2 of SMART are also presented.

Original language	English (US)
Publisher	SSRN
Number of pages	10
DOIs	https://doi.org/10.2139/ssrn.4296267
State	Published - Dec 20 2022

Keywords

ISGS
CO2 storage
machine learning
real-time decisions
reservoir management

Online availability

10.2139/ssrn.4296267

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4296267

Library availability

Discover UIUC Full Text

Cite this

Bromhal, G., Mishra, S., Guthrie, G., Aminzadeh, F., Crandall, D., Alumbaugh, D., White, J., Williams-Stroud, S., Azzolina, N., Yonkofski, C., McGuire, T., Pawar, R., Schuetter, J., Morris, J., Butler, S., Viswanathan, H., & Carr, T. (2022). The SMART Initiative: Applying Machine Learning to Enable Efficient and Effective Real-Time Decisions for Geological Carbon Storage Operations. SSRN. https://doi.org/10.2139/ssrn.4296267

Bromhal, G, Mishra, S, Guthrie, G, Aminzadeh, F, Crandall, D, Alumbaugh, D, White, J, Williams-Stroud, S, Azzolina, N, Yonkofski, C, McGuire, T, Pawar, R, Schuetter, J, Morris, J, Butler, S, Viswanathan, H & Carr, T 2022 'The SMART Initiative: Applying Machine Learning to Enable Efficient and Effective Real-Time Decisions for Geological Carbon Storage Operations' SSRN. https://doi.org/10.2139/ssrn.4296267

@techreport{1a520e782ac648cab5604ac0fa50a686,

title = "The SMART Initiative: Applying Machine Learning to Enable Efficient and Effective Real-Time Decisions for Geological Carbon Storage Operations",

abstract = "This paper provides an overview of the SMART Initiative – Science-Informed Machine Learning for Accelerating Real-Time Decisions in Subsurface Applications – that seeks to transform our interactions within and understanding of the subsurface, and significantly improve efficiency and effectiveness of field-scale carbon storage and unconventional oil and gas operations. The accomplishments of the recently concluded “proof-of-concept” Phase 1 are described. Goals for the “field deployement” of ML-assisted tools and workflows for both greenfield (i.e., pre-injection permitting) and brownfield (i.e., active injection operational control and post-injection site care) applications in Phase 2 of SMART are also presented.",

keywords = "ISGS, CO2 storage, machine learning, real-time decisions, reservoir management",

author = "Grant Bromhal and Srikanta Mishra and George Guthrie and Fred Aminzadeh and Dustin Crandall and David Alumbaugh and Joshua White and Sherilyn Williams-Stroud and Nicholas Azzolina and Catherine Yonkofski and Tom McGuire and Rajesh Pawar and Jared Schuetter and Joseph Morris and Shane Butler and Hari Viswanathan and Tim Carr",

year = "2022",

month = dec,

day = "20",

doi = "10.2139/ssrn.4296267",

language = "English (US)",

publisher = "SSRN",

type = "WorkingPaper",

institution = "SSRN",

}

TY - UNPB

T1 - The SMART Initiative: Applying Machine Learning to Enable Efficient and Effective Real-Time Decisions for Geological Carbon Storage Operations

AU - Bromhal, Grant

AU - Mishra, Srikanta

AU - Guthrie, George

AU - Aminzadeh, Fred

AU - Crandall, Dustin

AU - Alumbaugh, David

AU - White, Joshua

AU - Williams-Stroud, Sherilyn

AU - Azzolina, Nicholas

AU - Yonkofski, Catherine

AU - McGuire, Tom

AU - Pawar, Rajesh

AU - Schuetter, Jared

AU - Morris, Joseph

AU - Butler, Shane

AU - Viswanathan, Hari

AU - Carr, Tim

PY - 2022/12/20

Y1 - 2022/12/20

N2 - This paper provides an overview of the SMART Initiative – Science-Informed Machine Learning for Accelerating Real-Time Decisions in Subsurface Applications – that seeks to transform our interactions within and understanding of the subsurface, and significantly improve efficiency and effectiveness of field-scale carbon storage and unconventional oil and gas operations. The accomplishments of the recently concluded “proof-of-concept” Phase 1 are described. Goals for the “field deployement” of ML-assisted tools and workflows for both greenfield (i.e., pre-injection permitting) and brownfield (i.e., active injection operational control and post-injection site care) applications in Phase 2 of SMART are also presented.

AB - This paper provides an overview of the SMART Initiative – Science-Informed Machine Learning for Accelerating Real-Time Decisions in Subsurface Applications – that seeks to transform our interactions within and understanding of the subsurface, and significantly improve efficiency and effectiveness of field-scale carbon storage and unconventional oil and gas operations. The accomplishments of the recently concluded “proof-of-concept” Phase 1 are described. Goals for the “field deployement” of ML-assisted tools and workflows for both greenfield (i.e., pre-injection permitting) and brownfield (i.e., active injection operational control and post-injection site care) applications in Phase 2 of SMART are also presented.

KW - ISGS

KW - CO2 storage

KW - machine learning

KW - real-time decisions

KW - reservoir management

U2 - 10.2139/ssrn.4296267

DO - 10.2139/ssrn.4296267

M3 - Preprint

BT - The SMART Initiative: Applying Machine Learning to Enable Efficient and Effective Real-Time Decisions for Geological Carbon Storage Operations

PB - SSRN

ER -

The SMART Initiative: Applying Machine Learning to Enable Efficient and Effective Real-Time Decisions for Geological Carbon Storage Operations

Abstract

Keywords

Online availability

Library availability

Fingerprint

Cite this