Generating Subsurface Earth Models using Discrete Representation Learning and Deep Autoregressive Network

Subsurface earth models (referred to as geo-models) are crucial for characterizing complex subsurface systems. Multiple-point statistics are commonly used to generate geo-models. In this paper, a deep-learning-based generative method is developed as an alternative to the traditional Geomodel generat...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-02
Hauptverfasser:	Chen, Jungang, Chung-Kan, Huang, Delgado, Jose F, Misra, Siddharth
Format:	Artikel
Sprache:	eng
Schlagworte:	Autoregressive models Compression ratio Constraint modelling Deep learning Earth models Image manipulation Physics - Geophysics Representations Workflow
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!