Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks
Proceedings of the National Academy of Sciences · 21.04.2026 · 123 (16)
DOI: 10.1073/pnas.2508144123 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 17.04.2026. Verfasst von Mars Liyao Gao und 2 weiteren Autor:innen. Beteiligte Einrichtung: Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA 98195. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 111 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation (NSF), DOD | AF | AMC | AFRL | Air Force Office of Scientific Research (AFOSR).
Abstract (Originalsprache)
Modeling real-world spatiotemporal data is exceptionally difficult due to inherent high dimensionality, measurement noise, partial observations, and often expensive data collection procedures. In this paper, we present Sparse Identification of Nonlinear Dynamics with SHallow REcurrent Decoder networks (SINDy-SHRED), a method to jointly solve the sensing and model identification problems with simple implementation, efficient computation, and robust performance. SINDy-SHRED uses Gated Recurrent Units to model the temporal sequence of sparse sensor measurements along with a shallow decoder network to reconstruct the full spatiotemporal field from the latent state space. Our algorithm introduces a SINDy-based regularization for which the latent space progressively converges to a SINDy-class functional, provided the projection remains within the set. In restricting SINDy to a linear model, a Koopman-SHRED model is generated. SINDy-SHRED i) learns a symbolic and interpretable generative model of a parsimonious and low-dimensional latent space for the complex spatiotemporal dynamics, ii) discovers governing equations even for well-known physical systems, iii) achieves an observed convex loss landscape, and iv) achieves superior accuracy, data efficiency, and training cost, all with fewer model parameters, than competing state-of-the-art methods. We conduct systematic experimental studies on Partial differential equation data such as turbulent flows, real-world sensor measurements for sea surface temperature, and direct video data. The interpretable SINDy and Koopman models of latent state dynamics enable stable and accurate long-term video predictions, outperforming all current baseline deep learning models in accuracy, training cost, and data requirements, including Convolutional LSTM, PredRNN, ResNet, and SimVP.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA 98195.
- Department of Mechanical Engineering, University of Washington, Seattle, WA 98195.
- Department of Applied Mathematics, University of Washington, Seattle, WA 98195.
- Department of Electrical and Computer Engineering, University of Washington, Seattle, WA 98195.
ORCID-Profile: Mars Liyao Gao, J Nathan Kutz
Förderung
- National Science Foundation (NSF)
- DOD | AF | AMC | AFRL | Air Force Office of Scientific Research (AFOSR)
Zitieren
APA
Gao, M. L., Williams, J. P., & Kutz, J. N. (2026). Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks. Proceedings of the National Academy of Sciences, 123(16). https://doi.org/10.1073/pnas.2508144123
Vancouver
Gao ML, Williams JP, Kutz JN. Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks. Proceedings of the National Academy of Sciences. 2026;123(16). doi:10.1073/pnas.2508144123
BibTeX
@article{Gao2026,
author = {Gao, Mars Liyao and Williams, Jan P and Kutz, J Nathan},
title = {Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks},
journal = {Proceedings of the National Academy of Sciences},
year = {2026},
volume = {123},
number = {16},
doi = {10.1073/pnas.2508144123}
}
EUVIMED