Ensemble Gradient for Learning Turbulence Models from Indirect Observations

DOI10.4208/cicp.OA-2021-0082zbMath1491.76040arXiv2104.07811MaRDI QIDQ5065144

Heng Xiao, Xin-Lei Zhang, Carlos A. Michelén Ströfer

Publication date: 18 March 2022

Published in: Communications in Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2104.07811

zbMATH Keywords

Reynolds-averaged Navier-Stokes equationsdeep learningdeep neural networkensemble approximationtraining data-driven turbulence model

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Turbulence (76F99) Basic methods in fluid mechanics (76M99) Flow control and optimization for incompressible viscous fluids (76D55) Mathematical modeling or simulation for problems pertaining to fluid mechanics (76-10)

Related Items (3)

Ensemble Kalman method for learning turbulence models from indirect observation data ⋮ Artificial neural network based response surface for data-driven dimensional analysis ⋮ Combining direct and indirect sparse data for learning generalizable turbulence models

Uses Software

• DAFI

Cites Work

• Unnamed Item
• Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: a data-driven, physics-informed Bayesian approach
• Uncertainty quantification of reservoir performance predictions using a stochastic optimization algorithm
• RANS turbulence model development using CFD-driven machine learning
• Regularized ensemble Kalman methods for inverse problems
• On turbulent secondary flows in pipes of noncircular cross-section
• Theoretical connections between optimization algorithms based on an approximate gradient
• Multiple shooting shadowing for sensitivity analysis of chaotic dynamical systems
• Blackbox and derivative-free optimization: theory, algorithms and applications
• Reconstruction of unsteady viscous flows using data assimilation schemes
• Ensemble Kalman methods for inverse problems
• A continuous adjoint formulation for the computation of topological and surface sensitivities of ducted flows
• Introduction to Derivative-Free Optimization
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• A more general effective-viscosity hypothesis
• Inverse Problem Theory and Methods for Model Parameter Estimation
• Gradient-Based Aerodynamic Robust Optimization Using the Adjoint Method and Gaussian Processes
• DAFI: An Open-Source Framework for Ensemble-Based Data Assimilation and Field Inversion
• Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
• Analysis of the Ensemble Kalman Filter for Inverse Problems
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• Turbulence Modeling in the Age of Data

This page was built for publication: Ensemble Gradient for Learning Turbulence Models from Indirect Observations