期刊
出版社
ROYAL SOC
DOI: 10.1098/rspa.2017.0844
关键词
data-driven forecasting; long short-term memory; Gaussian processes; T21 barotropic climate model; Lorenz 96
资金
- Air Force Office of Scientific Research grant [FA9550-16-1-0231]
- Office of Naval Research grant [N00014-15-1-2381]
- Army Research Office grant [66710-EG-YIP]
- European Research Council (ERC) Advanced Investigator Award [341117]
We introduce a data-driven forecasting method for high-dimensional chaotic systems using long shortterm 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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据