eprintid: 19101
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/91/01
datestamp: 2024-06-04 14:11:33
lastmod: 2024-06-04 14:11:33
status_changed: 2024-06-04 14:04:52
type: book
metadata_visibility: show
creators_name: Rehman, A.N.
creators_name: Lal, B.
title: Machine Learning in CO2 Sequestration
ispublished: pub
note: cited By 0
abstract: CO2 capture and sequestration is a prominent field of study with high research demands. It involves capturing CO2 from various large point sources and storing it to prevent its emission. Various conventional CO2 sequestration techniques currently in practice involve CO2 storage in geological formations such as depleted oil and gas reservoirs, saline aquifers, and enhanced oil recovery (EOR) applica­tions. Another emerging technique is to store CO2 in the hydrate form in marine sedi­ments owing to its large storage capacity. Gas hydrates are crystalline solid struc­tures formed by the physical combination of gas (such as methane, carbon dioxide, propane, etc.) and water molecules at high-pressure and low-temperature condi­tions. This chapter briefly describes the conventional CO2 sequestration techniques with the challenges encountered in their application. Further, the chapter discusses the use of machine learning in gas hydrate related studies particularly concerning hydrate-based CO2 capture and sequestration. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
date: 2023
publisher: Springer Nature
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85174755732&partnerID=40&md5=1fbcbf1b5a531e814534a473281c3b76
full_text_status: none
publication: Machine Learning and Flow Assurance in Oil and Gas Production
pagerange: 119-140
refereed: TRUE
isbn: 9783031242311; 9783031242304
citation:   Rehman, A.N. and Lal, B.  (2023) Machine Learning in CO2 Sequestration.     Springer Nature, pp. 119-140.  ISBN 9783031242311; 9783031242304