English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We examine the efficiency of Recurrent Neural Networks in forecasting thespatiotemporal dynamics of high dimensional and reduced order complex systemsusing Reservoir Computing (RC) and Backpropagation through time (BPTT) forgated network architectures. We highlight advantages and limitations of eachmethod and discuss their implementation for parallel computing architectures.We quantify the relative prediction accuracy of these algorithms for thelongterm forecasting of chaotic systems using as benchmarks the Lorenz-96 andthe Kuramoto-Sivashinsky (KS) equations. We find that, when the full statedynamics are available for training, RC outperforms BPTT approaches in terms ofpredictive performance and in capturing of the long-term statistics, while atthe same time requiring much less training time. However, in the case ofreduced order data, large scale RC models can be unstable and more likely thanthe BPTT algorithms to diverge. In contrast, RNNs trained via BPTT showsuperior forecasting abilities and capture well the dynamics of reduced ordersystems. Furthermore, the present study quantifies for the first time theLyapunov Spectrum of the KS equation with BPTT, achieving similar accuracy asRC. This study establishes that RNNs are a potent computational framework forthe learning and forecasting of complex spatiotemporal systems.

Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamics