Hands On Scientific Machine Learning - SINDy

From the SciML group at Leeds Institute for Data Analytics

Speaker - Alasdair Roy, PhD Student, CDT Fluid Dynamics, University of Leeds

Description:
Alasdair Roy talks about the SINDy method and the accompanying Python package (PySINDy). SINDy is a sparse regression package, which allows symbolic identification of dynamical system from time series measurements. This makes SINDy different to black box methods, as finding underlying governing equations of motions allows for physical interpretation of the system, potentially allowing for greater generalisability of the resulting model.

Bio:
Alasdair Roy is working on reduced-order modelling methods using the sparse identification of nonlinear dynamics (SINDy). In his research, he uses SINDy to identify dynamical systems from magnetoconvection simulation data by seeing what characteristics of the data we are trying to reproduce.

Slides & References - https://sciml-leeds.github.io/assets/...