Bazhenov Fm Classification Based on Wireline Logs

Dettagli Bibliografici
Parent link:IOP Conference Series: Earth and Environmental Science
Vol. 33 : Contemporary Issues of Hydrogeology, Engineering Geology and Hydrogeoecology in Eurasia.— 2016.— [012034, 5 p.]
Autore principale: Simonov D. A. Dmitry Arturovich
Ente Autore: Национальный исследовательский Томский политехнический университет (ТПУ) Институт природных ресурсов (ИПР) Центр подготовки и переподготовки специалистов нефтегазового дела (ЦППС НД) Лаборатория геологии месторождений нефти и газа (ЛГМНГ)
Altri autori: Baranov V. E. Vitaliy Evgenievich, Bukhanov N. V. Nikita Vladimirovich
Riassunto:Title screen
This paper considers the main aspects of Bazhenov Formation interpretation and application of machine learning algorithms for the Kolpashev type section of the Bazhenov Formation, application of automatic classification algorithms that would change the scale of research from small to large. Machine learning algorithms help interpret the Bazhenov Formation in a reference well and in other wells. During this study, unsupervised and supervised machine learning algorithms were applied to interpret lithology and reservoir properties. This greatly simplifies the routine problem of manual interpretation and has an economic effect on the cost of laboratory analysis.
Lingua:inglese
Pubblicazione: 2016
Serie:Well drilling
Soggetti:
Accesso online:http://dx.doi.org/10.1088/1755-1315/33/1/012034
http://earchive.tpu.ru/handle/11683/33992
Natura: Elettronico Capitolo di libro
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=649495
Descrizione
Riassunto:Title screen
This paper considers the main aspects of Bazhenov Formation interpretation and application of machine learning algorithms for the Kolpashev type section of the Bazhenov Formation, application of automatic classification algorithms that would change the scale of research from small to large. Machine learning algorithms help interpret the Bazhenov Formation in a reference well and in other wells. During this study, unsupervised and supervised machine learning algorithms were applied to interpret lithology and reservoir properties. This greatly simplifies the routine problem of manual interpretation and has an economic effect on the cost of laboratory analysis.
DOI:10.1088/1755-1315/33/1/012034