Recurrent Deep Kernel Learning of Dynamical Systems
Abstract
Digital twins require computationally-efficient reduced-order models (ROMs) that can accurately describe complex dynamics of physical assets. However, constructing ROMs from noisy high-dimensional data is challenging. In this work, we propose a data-driven, non-intrusive method that utilizes stochastic variational deep kernel learning (SVDKL) to discover low-dimensional latent spaces from data and a recurrent version of SVDKL for representing and predicting the evolution of latent dynamics. The proposed method is demonstrated with two challenging examples -- a double pendulum and a reaction-diffusion system. Results show that our framework is capable of (i) denoising and reconstructing measurements, (ii) learning compact representations of system states, (iii) predicting system evolution in low-dimensional latent spaces, and (iv) quantifying modeling uncertainties.
Cite
@article{arxiv.2405.19785,
title = {Recurrent Deep Kernel Learning of Dynamical Systems},
author = {Nicolò Botteghi and Paolo Motta and Andrea Manzoni and Paolo Zunino and Mengwu Guo},
journal= {arXiv preprint arXiv:2405.19785},
year = {2024}
}