Long-term Prediction of Nonlinear Time Series Using Autoencoder and Echo State Networks

no code implementations • ICLR 2022 • Shahrokh Shahi, Flavio H. Fenton, Elizabeth M. Cherry

Not only do the computational results demonstrate improvements in prediction accuracy and robustness compared to mainstream data-driven approaches for chaotic time series forecasting, such as the baseline and physics-informed ESNs, but the representation provided by the feature extraction component in this technique also removes the requirement in related previous work for explicitly introducing additional exogenous time series to the network, which normally are not available in real-world applications.

Time Series Time Series Forecasting