Auto-Encoded Reservoir Computing for Turbulence Learning

12/20/2020
by   Nguyen Anh Khoa Doan, et al.
0

We present an Auto-Encoded Reservoir-Computing (AE-RC) approach to learn the dynamics of a 2D turbulent flow. The AE-RC consists of a Convolutional Autoencoder, which discovers an efficient manifold representation of the flow state, and an Echo State Network, which learns the time evolution of the flow in the manifold. The AE-RC is able to both learn the time-accurate dynamics of the turbulent flow and predict its first-order statistical moments. The AE-RC approach opens up new possibilities for the spatio-temporal prediction of turbulent flows with machine learning.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 5

page 6

02/15/2021

Short- and long-term prediction of a chaotic flow: A physics-constrained reservoir computing approach

We propose a physics-constrained machine learning method-based on reserv...
12/02/2019

Road traffic reservoir computing

Reservoir computing derived from recurrent neural networks is more appli...
12/23/2019

A physics-aware machine to predict extreme events in turbulence

We propose a physics-aware machine learning method to time-accurately pr...
01/28/2020

Reservoir computing model of two-dimensional turbulent convection

Reservoir computing is applied to model the large-scale evolution and th...
01/08/2019

Deep Neural Networks Predicting Oil Movement in a Development Unit

We present a novel technique for assessing the dynamics of multiphase fl...
05/25/2021

Connect the Dots: In Situ 4D Seismic Monitoring of CO_2 Storage with Spatio-temporal CNNs

4D seismic imaging has been widely used in CO_2 sequestration projects t...
04/28/2019

A General Spatio-Temporal Clustering-Based Non-local Formulation for Multiscale Modeling of Compartmentalized Reservoirs

Representing the reservoir as a network of discrete compartments with ne...
This week in AI

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