Online model learning with data-assimilated reservoir computers
This work addresses scalable online model learning for nonlinear time series forecasting in fluid dynamics, offering incremental improvements by unifying data-driven reduced order modeling with Bayesian data assimilation.
The authors tackled the problem of forecasting nonlinear spatio-temporal signals by proposing an online learning framework that integrates dimensionality reduction, a reservoir computer for forecasting, and ensemble sequential data assimilation for model updates. They demonstrated this on a cylinder wake flow, showing that a two-fold estimation strategy significantly improves ensemble convergence and reduces reconstruction error, while a three-fold approach enables robust online training of partially-trained reservoir computers.
We propose an online learning framework for forecasting nonlinear spatio-temporal signals (fields). The method integrates (i) dimensionality reduction, here, a simple proper orthogonal decomposition (POD) projection; (ii) a generalized autoregressive model to forecast reduced dynamics, here, a reservoir computer; (iii) online adaptation to update the reservoir computer (the model), here, ensemble sequential data assimilation. We demonstrate the framework on a wake past a cylinder governed by the Navier-Stokes equations, exploring the assimilation of full flow fields (projected onto POD modes) and sparse sensors. Three scenarios are examined: a naïve physical state estimation; a two-fold estimation of physical and reservoir states; and a three-fold estimation that also adjusts the model parameters. The two-fold strategy significantly improves ensemble convergence and reduces reconstruction error compared to the naïve approach. The three-fold approach enables robust online training of partially-trained reservoir computers, overcoming limitations of a priori training. By unifying data-driven reduced order modelling with Bayesian data assimilation, this work opens new opportunities for scalable online model learning for nonlinear time series forecasting.