Model-Free Forecasting of Partially Observable Spatiotemporally Chaotic Systems

TL;DR

This paper introduces a reservoir computing approach with nonlinear projectors, enabling accurate, model-free forecasting of partially observed, noisy, and complex turbulent systems without full state knowledge.

Contribution

It demonstrates a novel use of nonlinear projector functions in reservoir computing to handle partial observations and unknown nonlinearities in chaotic systems.

Findings

Radial basis functions effectively capture system nonlinearities.

The method maintains forecast accuracy with sparse, noisy, and incomplete data.

It enables model-free turbulence forecasting without full system knowledge.

Abstract

Reservoir computing is a powerful tool for forecasting turbulence because its simple architecture has the computational efficiency to handle large systems. Its implementation, however, often requires full state-vector measurements and knowledge of the system nonlinearities. We use nonlinear projector functions to expand the system measurements to a high dimensional space and then feed them to a reservoir to obtain forecasts. We demonstrate the application of such reservoir computing networks on spatiotemporally chaotic systems, which model several features of turbulence. We show that using radial basis functions as nonlinear projectors enables complex system nonlinearities to be captured robustly even with only partial observations and without knowing the governing equations. Finally, we show that when measurements are sparse or incomplete and noisy, such that even the governing equations become inaccurate, our networks can still produce reasonably accurate forecasts, thus paving the way towards model-free forecasting of practical turbulent systems.