Journal Article

Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks

Wan, Zhong Y., Byeon, Wonmin, Sapsis, Themistoklis P., Koumoutsakos, Petros, Vlachas, Pantelis R.

2018

Overview

We introduce a data-driven forecasting method for high-dimensional chaotic systems using long short-term memory (LSTM) recurrent neural networks. The proposed LSTM neural networks perform inference of high-dimensional dynamical systems in their reduced order space and are shown to be an effective set of nonlinear approximators of their attractor. We demonstrate the forecasting performance of the LSTM and compare it with Gaussian processes (GPs) in time series obtained from the Lorenz 96 system, the Kuramoto–Sivashinsky equation and a prototype climate model. The LSTM networks outperform the GPs in short-term forecasting accuracy in all applications considered. A hybrid architecture, extending the LSTM with a mean stochastic model (MSM–LSTM), is proposed to ensure convergence to the invariant measure. This novel hybrid method is fully data-driven and extends the forecasting capabilities of LSTM networks.

• Publisher: The Royal Society Publishing
• Subject: Chaos theory / Climate models / Computer memory / Data-Driven Forecasting / Forecasting / Gaussian process / Gaussian Processes / Long Short-Term Memory / Lorenz 96 / Model reduction / Recurrent neural networks / Short term / T21 Barotropic Climate Model