This is a testbed for system identification and forecasting of dynamical systems using the Hankel Alternative View of Koopman (HAVOK) algorithm and Sparse Identification of Nonlinear Dynamics (SINDy). This code is based on the work by Brunton & Kutz (2022) and Yang et. al. (2022).
MIT License
1
stars
0
forks
source link
HAVOK-ML model blows up after a long enough simulation #13
Even when the ML method, in this case a Random Forest Regressor (RFR) is well-trained:
It quickly diverges when run in conjunction with the HAVOK model:
Leading to exponential growth in x:
Settings: stackmax=40, rmax=4, degOfSparsity=1e-5, polyDegree=1.