3D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodels

by   Yimin Liu, et al.

Geological parameterization enables the representation of geomodels in terms of a relatively small set of variables. Parameterization is therefore very useful in the context of data assimilation and uncertainty quantification. In this study, a deep-learning-based geological parameterization algorithm, CNN-PCA, is developed for complex 3D geomodels. CNN-PCA entails the use of convolutional neural networks as a post-processor for the low-dimensional principal component analysis representation of a geomodel. The 3D treatments presented here differ somewhat from those used in the 2D CNN-PCA procedure. Specifically, we introduce a new supervised-learning-based reconstruction loss, which is used in combination with style loss and hard data loss. The style loss uses features extracted from a 3D CNN pretrained for video classification. The 3D CNN-PCA algorithm is applied for the generation of conditional 3D realizations, defined on 60×60×40 grids, for three geological scenarios (binary and bimodal channelized systems, and a three-facies channel-levee-mud system). CNN-PCA realizations are shown to exhibit geological features that are visually consistent with reference models generated using object-based methods. Statistics of flow responses (P_10, P_50, P_90 percentile results) for test sets of 3D CNN-PCA models are shown to be in consistent agreement with those from reference geomodels. Lastly, CNN-PCA is successfully applied for history matching with ESMDA for the bimodal channelized system.



There are no comments yet.


page 8

page 9

page 14

page 15

page 18

page 21

page 27

page 28


A Deep-Learning-Based Geological Parameterization for History Matching Complex Models

A new low-dimensional parameterization based on principal component anal...

A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems

A deep-learning-based surrogate model is developed and applied for predi...

Separation of cardiac and respiratory components from the electrical bio-impedance signal using PCA and fast ICA

This paper is an attempt to separate cardiac and respiratory signals fro...

Robust Learning with Kernel Mean p-Power Error Loss

Correntropy is a second order statistical measure in kernel space, which...

Uncertainty Quantification in CNN-Based Surface Prediction Using Shape Priors

Surface reconstruction is a vital tool in a wide range of areas of medic...

Deep Learning for Automatic Quality Grading of Mangoes: Methods and Insights

The quality grading of mangoes is a crucial task for mango growers as it...

Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother

The literature about history matching is vast and despite the impressive...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.