Comparison of Seismic Traces Clustering Efficiency of Different Unsupervised Machine Learning Algorithms in Forward Seismic Models; 81st EAGE Conference and Exhibition 2019

Comparison of Seismic Traces Clustering Efficiency of Different Unsupervised Machine Learning Algorithms in Forward Seismic Models; 81st EAGE Conference and Exhibition 2019

Dades bibliogràfiques
Parent link:81st EAGE Conference and Exhibition 2019.— 2019.— [4 p.]
Autor corporatiu: 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), Национальный исследовательский Томский политехнический университет Институт природных ресурсов Центр подготовки и переподготовки специалистов нефтегазового дела
Altres autors: Churochkin I. I. Iljya Igorevich, Volkova A. A. Aleksandra Aleksandrovna, Gavrilova E., Bukhanov N. V. Nikita Vladimirovich, Butorin A. V. Aleksandr Vasiljevich, Rukavishnikov V. S. Valery Sergeevich
Sumari:Title screen
In this study, it is proposed to build geological model based on proportions of fluvial deposits outcrop. Then forward seismic model is constructed and clustering of seismic traces by using different unsupervised algorithms (k-means, DBSCAN and Agglomerative clustering) is performed. Results are compared with ground truth, which in our case is NTG map of interval of interest in geological model. Finally the optimal settings of the algorithms and the most accurate clustering method are identified.
Режим доступа: по договору с организацией-держателем ресурса
Idioma:anglès
Publicat: 2019
Col·lecció:AI/Digitalization for Interpretation - Various Application
Matèries:
электронный ресурс
труды учёных ТПУ
сейсмические трассы
неконтролируемые процессы
Accés en línia:https://doi.org/10.3997/2214-4609.201901390
Format: Electrònic Capítol de llibre
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=660618
Descripció
Sumari:Title screen
In this study, it is proposed to build geological model based on proportions of fluvial deposits outcrop. Then forward seismic model is constructed and clustering of seismic traces by using different unsupervised algorithms (k-means, DBSCAN and Agglomerative clustering) is performed. Results are compared with ground truth, which in our case is NTG map of interval of interest in geological model. Finally the optimal settings of the algorithms and the most accurate clustering method are identified.
Режим доступа: по договору с организацией-держателем ресурса
DOI:10.3997/2214-4609.201901390

Ítems similars