SciML / DataDrivenDiffEq.jl

Data driven modeling and automated discovery of dynamical systems for the SciML Scientific Machine Learning organization
https://docs.sciml.ai/DataDrivenDiffEq/stable/
MIT License
406 stars 57 forks source link

Hankel-DMD #5

Open ChrisRackauckas opened 4 years ago

ChrisRackauckas commented 4 years ago

https://sites.engineering.ucsb.edu/~harbabi/research/M112523.pdf

AlCap23 commented 4 years ago

If the embedding is given, than HAVOK might be also nice.

https://www.nature.com/articles/s41467-017-00030-8.pdf

agerlach commented 4 years ago

I have had good success using time-delay embeddings as observables. FYI, DynamicalSystems.jl has some delay embedding capabilities with algorithms for optimizing the embedding. See: Delay Embeddings

AlCap23 commented 4 years ago

Thanks! I am a little bit anxious because that would mean using the DataSet type :) But I will definitely have a look.

Did you use them within DataDrivenDiffEq? Or in general?

agerlach commented 4 years ago

I hacked around with it on my own before DataDrivenDiffEq was a thing. I agree completely regarding DataSet.