Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Cheolkyun Jeong"'
Autor:
Gregory Skoff, Fatma Mahfoudh, Cheolkyun Jeong, Sergey Makarychev-Mikhailov, Oleh Petryshak, Velizar Vesselinov, Crispin Chatar, Vijay Bondale, Manju Devadas
Publikováno v:
Day 3 Thu, March 09, 2023.
The energy industry is undergoing a digital transformation, whose goals include increased operational efficiency and reduced energy extraction costs. Data science and machine learning (ML) are enabling the drilling engineering community to contribute
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50d41b13b5f0d478458a35117eb096bb
https://doi.org/10.2118/212559-ms
https://doi.org/10.2118/212559-ms
Publikováno v:
Day 2 Wed, March 09, 2022.
The industry has focused mainly on extracting key performance indicators (KPI) from its operational processes that aggregate data in different forms. The computation of average values has been one of the most important ways to measure process perform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7bc181dbccebc646081b52b4a26e4d2d
https://doi.org/10.2118/208676-ms
https://doi.org/10.2118/208676-ms
Publikováno v:
Day 1 Tue, March 08, 2022.
Operators drilling a directional well may suffer the uncertainties from the downhole environment, the equipment, and the human decision-making process. We proposed a method to evaluate steering decisions of multiple reinforcement learning agents by c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9bf3d5d88cc0615a59b88649b33cb92e
https://doi.org/10.2118/208736-ms
https://doi.org/10.2118/208736-ms
Publikováno v:
Day 1 Tue, March 03, 2020.
One of the practical challenges in the oil and gas industry is the lack of quality data for applying machine learning techniques. A way to tackle this problem is to build a hybrid system that combines physics models with machine learning workflows. T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::71ebbac6817abaadad823acb8bed312f
https://doi.org/10.2118/199629-ms
https://doi.org/10.2118/199629-ms
Publikováno v:
Mathematical Geosciences. 49:845-869
Seismic inverse modeling, which transforms appropriately processed geophysical data into the physical properties of the Earth, is an essential process for reservoir characterization. This paper proposes a work flow based on a Markov chain Monte Carlo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ba360d72dd04db5dd795777162636cc
https://doi.org/10.1007/s11004-017-9693-y
https://doi.org/10.1007/s11004-017-9693-y
Publikováno v:
Energy Sources, Part A: Recovery, Utilization, and Environmental Effects. 35:66-76
A new integrated model of statistical pre-treatment and fuzzy logic is developed to predict unknown permeabilities from well logs. The log treatment based on factor analysis and clustering characterizes statistically electrofacies that are the input
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6823e8eae5230db4d3e90689ce6a3d8
https://doi.org/10.1080/15567030903515021
https://doi.org/10.1080/15567030903515021
Publikováno v:
Volume 8: Polar and Arctic Sciences and Technology; Petroleum Technology.
This study determines facies distribution in a clastic reservoir using a hidden Markov model combined with an Expectation-Maximization algorithm. Iterating expectation and maximization steps of the algorithm builds the hidden Markov model by tuning t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b75c0fd02245a7755e5a7949841c9c39
https://doi.org/10.1115/omae2016-54773
https://doi.org/10.1115/omae2016-54773
Publikováno v:
SEG Technical Program Expanded Abstracts 2014.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a65ab1785a2c67bf781b5fba6dbad55f
https://doi.org/10.1190/segam2014-1092.1
https://doi.org/10.1190/segam2014-1092.1
Publikováno v:
SEG Technical Program Expanded Abstracts 2012.
Summary Seismic reservoir characterization aims to transform obtained seismic signatures into reservoir properties such as lithofacies and pore fluids. We propose a Markov chain Monte Carlo (McMC) workflow consistent with geology, well-logs, seismic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5a69634cbe4ecd9d582ea6b67561ae19
https://doi.org/10.1190/segam2012-0625.1
https://doi.org/10.1190/segam2012-0625.1
Publikováno v:
SEG Technical Program Expanded Abstracts 2011.
Inverse modeling, which transforms obtained geophysical data into physical properties of the Earth, is an essential process for reservoir characterization. We propose a Markov chain Monte Carlo (McMC) workflow consistent with geology, well-logs, seis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d749e3e20b6476fc06821a5da6479804
https://doi.org/10.1190/1.3627547
https://doi.org/10.1190/1.3627547