Sparse Nonlinear Models for Fluid Dynamics with Machine Learning and Optimization

Показать описание

Reduced-order models of fluid flows are essential for real-time control, prediction, and optimization of engineering systems that involve a working fluid. The sparse identification of nonlinear dynamics (SINDy) algorithm is being used to develop nonlinear models for complex fluid flows that balance accuracy and efficiency. We explore recent innovations related to several complex flow fields: bluff body wakes, cavity flows, thermal and electro convection, and magnetohydrodynamics.

Papers in order:

@eigensteve on Twitter

This video was produced at the University of Washington

%%% CHAPTERS %%%
0:00 Introduction
3:14 Interpretable and Generalizable Machine Learning
8:04 SINDy Overview
11:16 Discovering Partial Differential Equations
12:37 Deep Autoencoder Coordinates
13:42 Modeling Fluid Flows with Galerkin Regression
21:00 Chaotic thermo syphon
22:14 Chaotic electroconvection
25:52 Magnetohydrodynamics
27:40 Nonlinear correlations
29:47 Stochastic SINDy models for turbulence
32:54 Dominant balance physics modeling

Steve Brunton

Рекомендации по теме

Комментарии

I wonder how lucky are we. Viewing world class lectures from Indian village. That too without any cost. Thank you

js

Thanks for the video. The concept introduced in 2016 is like using dictionaries for dynamical systems and the follow up papers extends this work. Great work.

tytuer

Wow, this is such a great lecture. Thank you. I came for RL but I am staying for interpretable and generalizable models.

theodoreomtzigt

Thank you for your teaching, really good education for parametric architect, engineer like me, I really the chaos theory, Lorentz attractor & aerodynamics 👍👍👍🥂🦋✨

yiyangwu

Great Lecture sir, eagerly Waiting for Lagrangian coherent structure series

ashutoshsingh-etvm

gotta be honest steve. I'm disappointed that you didn't start with "welcome back"
that's half of the reason I watch your videos

morekaccino

Although randomness had often been viewed as an obstacle and a nuisance for many centuries, in the 20th century computer scientists began to realize that the deliberate introduction of randomness into computations can be an effective tool for designing better algorithms. In some cases, such randomized algorithms even outperform the best deterministic methods.

frankdelahue

Wow, I’ve done similar model fitting. Stepwise fitting does well to form a sparse model excluding parameters which are not physically involved. The challenge is identify the cutoff point where more parameters are not added.

rb

One of the best videos I've seen! It's amazing!

alaapsarkar

Great video! I was waiting for it. But my major doubt with syndy is finding the right base. In the future, you could make a lecture focus in ways to find the bases because this look like the greatest challenge.

vitorbortolin

Thank you for this very interesting lecture !
I should be starting a PhD in Applied Maths for Hydrology in the next few months and I would really like to apply POD+constrained SINDy methods for solving inverse problems on St-Venant equations. Do you think the PySindy library can be used to build easy-to-invert models for data assimilation ?
Thank you again for what you are doing, I’m a huge fan of your work ! Have a nice day.

Fyizze

Can these techniques be used for things like weather or climate simulations? Or are those too "chaotic" for sparse models to work?

kevalan

Spectacular work, thank you for sharing.

Janamejaya.Channegowda

How does sindy compare with genetic programming for system identification?

prajwol_poudel

Especially curious about the neuroscience applications. Maybe think also of other biological systems: immune system, virus evolution, ...

marc-andredesrosiers

Very interesting novel application! Expect some more app for the coupled with PB in future:)

hbbst

Really interesting... do you have plans to apply sindy to telecom network traffic analytics?

samferrer

Are there extensions of this for stochastic differential equations?

claytonestey

Really impressive and inspiring stuff! Thanks for sharing…it definitely stimulates ideas

jimlbeaver

Hey Steve, is this just a shorter version of the talk you did for 'critical transitions with complex systems'?

paladinofjustice

Sparse Nonlinear Models for Fluid Dynamics with Machine Learning and Optimization

Sparse Nonlinear Models for Fluid Dynamics with Machine Learning and Optimization

Sparse Identification of Nonlinear Dynamics (SINDy): Sparse Machine Learning Models 5 Years Later!

SINDy-PI: A robust algorithm for parallel implicit sparse identification of nonlinear dynamics

Sparse Nonlinear Dynamics Models with SINDy, Part 5: The Optimization Algorithms

Sparse Nonlinear Dynamics Models with SINDy, Part 2: Training Data & Disambiguating Models

Sparse Nonlinear Dynamics Models with SINDy, Part 3: Effective Coordinates for Parsimonious Models

System Identification: Sparse Nonlinear Models with Control

Machine Learning for Computational Fluid Dynamics

Machine Learning for Fluid Dynamics: Models and Control

ADDRESSING OVERFITTING ISSUES IN THE SPARSE IDENTIFICATION OF NONLINEAR DYNAMICAL SYSTEMS

Sparse Identification of Nonlinear Dynamics (SINDy)

Data-driven blood flow modeling with sparse representation (APS Division of Fluid Dynamics 2020)

Sparse Nonlinear Dynamics Models with SINDy, Part 4: The Library of Candidate Nonlinearities

Robust Model Discovery with Ensemble Learning and SINDy (applications to active learning & contr...

TomoFluid: Reconstructing Dynamic Fluid From Sparse View Videos

SINDy-PI: A Robust Algorithym for Parallel Implicit Sparse Identification of Nonlinear Dynamics

Robust, Interpretable Statistical Models: Sparse Regression with the LASSO

Steve Brunton: 'Discovering interpretable and generalizable dynamical systems from data'

Machine learning for scientific discovery with examples in fluid mechanics | AI for Good Webinar

BIGMECA : Efficient nonlinear manifold reduced order models with sparse shallow neural network

Machine Learning for Fluid Mechanics

Steve Brunton: 'Machine Learning for Fluid Mechanics'

Machine Learning for Fluid Dynamics: Patterns

Modeling synchronization in turbulent flows