Exploring the RCNN Technique in a Multiple-Point Statistics Framework

Loading...
Thumbnail Image

Authors

Avalos, Sebastian
Ortiz, Julian M.

Date

2019

Type

journal article

Language

en

Keyword

Research Projects

Organizational Units

Journal Issue

Alternative Title

Abstract

This work explores the Recursive Convolutional Neural Network (RCNN) technique in terms of describing (1) the inner architecture, (2) the training process and (3) the simulation algorithm in a multiple-point statistics simulation framework. To acquire a more intuitive understanding of the previous description, visualizations of hidden layers activations using three different training images is presented. Two interesting applications (1) using RCNN E-types as secondary information for MPS algorithms and (2) training RCNN with scarce and limited information, are also explored.

Description

This is a preprint version of a paper that was subsequently published in S. Avalos and J. M. Ortiz, “Recursive convolutional neural networks in a multiple-point statistics framework,” Computers & geosciences, vol. 141, p. 104522–, Aug. 2020, doi: 10.1016/j.cageo.2020.104522.. It does not contain changes and edits that were made during peer review, or updates, edits and alterations by the authors and the publisher that occurred prior to acceptance and final publication

Citation

Avalos S, Ortiz JM (2019) Exploring the RCNN technique in a multiple-point statistics framework, Predictive Geometallurgy and Geostatistics Lab, Queen’s University, Annual Report 2019, paper 2019-03, 30-40.

Publisher

Queen's University

Journal

Volume

Issue

PubMed ID

External DOI

ISSN

EISSN