search

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
402 stars 56 forks source link

Unable to recover the dynamic and predict, when DataDrivenSolution's problem is Discrete DataDrivenProblem #456

Closed MortezaBabazadehShareh closed 1 year ago

MortezaBabazadehShareh commented 1 year ago

I work with DataDrivenDiffEq and DifferentialEquations packages. Whenever I define a Discrete DataDrivenProblem and solve the problem(for example by Sindy), I cannot recover the dynamic form the DataDrivenSolution and make predictions. This happens in a situation that error is reasonably low and the plot function shows a relatively match graphs. The point is, it is not the case when I have a Continuous DataDrivenProblem. Here I put a link to an example of this problem:

https://github.com/MortezaBabazadehShareh/MortezaBabazadehShareh/blob/main/simulated_SIR.jl

ChrisRackauckas commented 1 year ago

It looks like this is just a duplicate of https://github.com/SciML/DataDrivenDiffEq.jl/issues/448