Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Learning Dynamical Systems from Partial Observations

About

We consider the problem of forecasting complex, nonlinear space-time processes when observations provide only partial information of on the system's state. We propose a natural data-driven framework, where the system's dynamics are modelled by an unknown time-varying differential equation, and the evolution term is estimated from the data, using a neural network. Any future state can then be computed by placing the associated differential equation in an ODE solver. We first evaluate our approach on shallow water and Euler simulations. We find that our method not only demonstrates high quality long-term forecasts, but also learns to produce hidden states closely resembling the true states of the system, without direct supervision on the latter. Additional experiments conducted on challenging, state of the art ocean simulations further validate our findings, while exhibiting notable improvements over classical baselines.

Ibrahim Ayed, Emmanuel de B\'ezenac, Arthur Pajot, Julien Brajard, Patrick Gallinari• 2019

Related benchmarks

TaskDatasetResultRank
Dynamical system modelingLotka-Volterra (LV) m=10, n=1 (train)
MSE0.457
7
Dynamical system modelingGray-Scott (GS) m=3, n=1 (train)
MSE0.0155
7
Dynamical system modelingNavier-Stokes (NS) m=4, n=8 (train)
MSE0.0517
7
Showing 3 of 3 rows

Other info

Follow for update