Data-driven predictions of a multiscale Lorenz 96 chaotic system using machine-learning methods: reservoir computing, artificial neural network, and long short-term memory network

dc.citation.firstpage373en_US
dc.citation.journalTitleNonlinear Processes in Geophysicsen_US
dc.citation.lastpage389en_US
dc.citation.volumeNumber27en_US
dc.contributor.authorChattopadhyay, Asheshen_US
dc.contributor.authorHassanzadeh, Pedramen_US
dc.contributor.authorSubramanian, Devikaen_US
dc.date.accessioned2020-10-16T18:17:13Zen_US
dc.date.available2020-10-16T18:17:13Zen_US
dc.date.issued2020en_US
dc.description.abstractIn this paper, the performance of three machine-learning methods for predicting short-term evolution and for reproducing the long-term statistics of a multiscale spatiotemporal Lorenz 96 system is examined. The methods are an echo state network (ESN, which is a type of reservoir computing; hereafter RC–ESN), a deep feed-forward artificial neural network (ANN), and a recurrent neural network (RNN) with long short-term memory (LSTM; hereafter RNN–LSTM). This Lorenz 96 system has three tiers of nonlinearly interacting variables representing slow/large-scale (X), intermediate (Y), and fast/small-scale (Z) processes. For training or testing, only X is available; Y and Z are never known or used. We show that RC–ESN substantially outperforms ANN and RNN–LSTM for short-term predictions, e.g., accurately forecasting the chaotic trajectories for hundreds of numerical solver's time steps equivalent to several Lyapunov timescales. The RNN–LSTM outperforms ANN, and both methods show some prediction skills too. Furthermore, even after losing the trajectory, data predicted by RC–ESN and RNN–LSTM have probability density functions (pdf's) that closely match the true pdf – even at the tails. The pdf of the data predicted using ANN, however, deviates from the true pdf. Implications, caveats, and applications to data-driven and data-assisted surrogate modeling of complex nonlinear dynamical systems, such as weather and climate, are discussed.en_US
dc.identifier.citationChattopadhyay, Ashesh, Hassanzadeh, Pedram and Subramanian, Devika. "Data-driven predictions of a multiscale Lorenz 96 chaotic system using machine-learning methods: reservoir computing, artificial neural network, and long short-term memory network." <i>Nonlinear Processes in Geophysics,</i> 27, (2020) Copernicus Publications: 373-389. https://doi.org/10.5194/npg-27-373-2020.en_US
dc.identifier.doihttps://doi.org/10.5194/npg-27-373-2020en_US
dc.identifier.urihttps://hdl.handle.net/1911/109424en_US
dc.language.isoengen_US
dc.publisherCopernicus Publicationsen_US
dc.rightsThis work is distributed under the Creative Commons Attribution 4.0 License.en_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_US
dc.titleData-driven predictions of a multiscale Lorenz 96 chaotic system using machine-learning methods: reservoir computing, artificial neural network, and long short-term memory networken_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
npg-27-373-2020.pdf
Size:
2.1 MB
Format:
Adobe Portable Document Format
Description: