Leveraging reduced-order models for state estimation using deep learning

DOI10.1017/jfm.2020.409zbMath1460.76174arXiv1912.10553OpenAlexW3100255097MaRDI QIDQ5113091

Nirmal J. Nair, Andres Goza

Publication date: 10 June 2020

Published in: Journal of Fluid Mechanics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.10553

zbMATH Keywords

computational methodsvortex sheddinglow-dimensional models

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Navier-Stokes equations for incompressible viscous fluids (76D05)

Related Items (5)

State estimation with limited sensors -- a deep learning based approach ⋮ Inadequacy of linear methods for minimal sensor placement and feature selection in nonlinear systems: a new approach using secants ⋮ Interpreted machine learning in fluid dynamics: explaining relaminarisation events in wall-bounded shear flows ⋮ Dynamics of a data-driven low-dimensional model of turbulent minimal Couette flow ⋮ Data-driven robust state estimation for reduced-order models of 2D Boussinesq equations with parametric uncertainties

Cites Work

• Unnamed Item
• A fast immersed boundary method using a nullspace approach and multi-domain far-field boundary conditions
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Sparse Sensor Placement Optimization for Classification
• Compressive sensing based machine learning strategy for characterizing the flow around a cylinder with limited pressure measurements
• Nonlinear model order reduction based on local reduced-order bases
• Dynamic mode decomposition of numerical and experimental data
• Machine Learning for Fluid Mechanics
• Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
• Sparse reduced-order modelling: sensor-based dynamics to full-state estimation
• Data-Driven Sparse Sensor Placement for Reconstruction: Demonstrating the Benefits of Exploiting Known Patterns
• Shallow neural networks for fluid flow reconstruction with limited sensors
• Linearly Recurrent Autoencoder Networks for Learning Dynamics

This page was built for publication: Leveraging reduced-order models for state estimation using deep learning