Helping Communicate Research Ideas to the Broader Community
Deep learning models for global coordinate transformations that linearize PDEs
This video highlights recent innovations for using neural networks for discovery of linearizing Koopman transformations for dynamics in complex systems. [View] [Code]
Data-driven Discovery of Governing Equations
This video highlights recent innovations for the targeted use of neural networks for discovery coordinates and dynamics in complex systems. [View]
Deep Learning of Hiearchical Multiscale Differential Equation Time Steppers
This video highlights how deep learning can be used to produce stable, multiscale time-stepping schemes. [View]
Data-driven Stabilization of Periodic Orbits
This video highlights how to stabilise periodic orbits using modern data-driven methods [View]
Deep Learning of Dynamics and Coordinates with SINDy Autoencoders
This video highlights recent innovations for discovering coordinates and dynamics jointly using deep learning [View]
PySINDy: A Python Library for Model Discovery
This video highlights an open source python package for model discovery [View]
From Fourier to Koopman: Spectral Methods for Forecasting
This video highlights recent innovations for long-time forecasting [View]
Models for Rotating Detonation Engines (RDEs)
This video highlights recent innovations for characterizing the detonation dynamics of rotating detonation engines [View]
Data-driven Discovery of Governing Equations
This video highlights recent innovations for discovering nonlinear dynamical systems from time series data. [View]
Data-driven sensor placement methods
This video highlights highlights data-driven methods and dimensionality reduction for optimal sensor placement. [View]
Data-driven methods for discovery of observables and Koopman embeddings in dynamical systems
This video highlights a presentation at the IPAM workshop on Collective Variables in Classical Mechanics (Workshop II from October 24-28, 2016). [View]
Primary collaborators Steven Brunton and Joshua Proctor
Hankel Alternative View of Koopman (HAVOK) Analysis
This video highlights a new algorithm to decompose chaos into a linear system with intermitting forcing. [View]
Inferring biological networks by sparse idendification of nonlinear dynamics
This video highlights the concepts of sparse regression for identifying nonlinear dynamical systems that are of the form dy/dt=f(y)/g(y) which often arise in biological networks. [View]
Discovering governing equations from data by sparse identification of nonlinear dynamical systems
This video highlights the recent innovation of using overcomplete libraries and sparse regression to discover nonlinear dynamical systems from time series data. [View]