paper-with-me

Papers

Learning Latent Dynamics for Partially-Observed Chaotic Systems

2019-07-04 · Said Ouala, Duong Nguyen, Lucas. Drumetz, Bertrand Chapron, Ananda Pascual, Fabrice Collard, Lucile Gaultier, Ronan Fablet

This paper addresses the data-driven identification of latent dynamical representations of partially-observed systems, i.e., dynamical systems for which some components are never observed, with an emphasis on forecasting applications, including long-term asymptotic patterns. Whereas state-of-the-art data-driven approaches rely 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 learn an ODE (Ordinary Differential Equation) representation in the latent space and reconstructing latent states. Through numerical experiments, we demonstrate the relevance of the proposed framework w.r.t. state-of-the-art approaches in terms of short-term forecasting performance and long-term behaviour. We further discuss how the proposed framework relates to Koopman operator theory and Takens' embedding theorem.

📄 PDF Abstract BibTeX arXiv:1907.02452

Code (1)

CIA-Oceanix/NbedDyn pytorch

Similar Papers 제목 키워드 기반

Learning partially observed systems with neural Hamiltonian ordinary differential equations

2026-05-22 · Sunniva Meltzer, Sølve Eidnes, Alexander Johannes Stasik arxiv

When learning dynamical systems from data, embedding physical structure can constrain the solution space and improve generalization, but many physics-informed models assume access to the full system state. This limits th…

Deep Learning of Chaotic Systems from Partially-Observed Data

2022-05-12 · Victor Churchill, Dongbin Xiu

Recently, a general data driven numerical framework has been developed for learning and modeling of unknown dynamical systems using fully- or partially-observed data. The method utilizes deep neural networks (DNNs) to co…

Deep Learning

Long-time accuracy of ensemble Kalman filters for chaotic and machine-learned dynamical systems

2024-12-18 · Daniel Sanz-Alonso, Nathan Waniorek

Filtering is concerned with online estimation of the state of a dynamical system from partial and noisy observations. In applications where the state is high dimensional, ensemble Kalman filters are often the method of c…

EM-like Learning Chaotic Dynamics from Noisy and Partial Observations

2019-03-25 · Duong Nguyen, Said Ouala, Lucas. Drumetz, Ronan Fablet

The identification of the governing equations of chaotic dynamical systems from data has recently emerged as a hot topic. While the seminal work by Brunton et al. reported proof-of-concepts for idealized observation sett…

Reconstructing shared dynamics with a deep neural network

2021-05-05 · Zsigmond Benkő, Zoltán Somogyvári

Determining hidden shared patterns behind dynamic phenomena can be a game-changer in multiple areas of research. Here we present the principles and show a method to identify hidden shared dynamics from time series by a t…

Time SeriesTime Series Analysis