Please use this identifier to cite or link to this item:
logo share SHARE logo core CORE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Learning latent dynamics for partially observed chaotic systems

AuthorsOuala, Said; Nguyen, Duong; Drumetz, L.; Chapron, Bertrand; Pascual, Ananda CSIC ORCID; Collard, Fabrice; Gaultier, L.; Fablet, Ronan
Issue Date20-Oct-2020
PublisherAmerican Institute of Physics
CitationChaos 30: 103121 (2020)
AbstractThis paper addresses the data-driven identification of latent representations of partially observed dynamical systems, i.e., dynamical systems for which some components are never observed, with an emphasis on forecasting applications and long-term asymptotic patterns. Whereas state-of-the-art data-driven approaches rely in general on delay embeddings and linear decompositions of the underlying operators, we introduce a framework based on the data-driven identification of an augmented state-space model using a neural-network-based representation. For a given training dataset, it amounts to jointly reconstructing the latent states and learning an ordinary differential equation representation in this space. Through numerical experiments, we demonstrate the relevance of the proposed framework with respect to state-of-the-art approaches in terms of short-term forecasting errors and long-term behavior. We further discuss how the proposed framework relates to the Koopman operator theory and Takens' embedding theorem.
Publisher version (URL)
Identifiersdoi: 10.1063/5.0019309
issn: 1054-1500
e-issn: 1089-7682
Appears in Collections:(IMEDEA) Artículos

Files in This Item:
File Description SizeFormat
observed_chaotic_systems.pdf3,57 MBAdobe PDFThumbnail
Show full item record
Review this work

Google ScholarTM




WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.