Integrated Utilization of Equations and Small Dataset in the Koopman Operator: Applications to Forward and Inverse Problems
Journal of the Physical Society of Japan · 15.06.2025 · 94 (6)
DOI: 10.7566/jpsj.94.064001 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Physical Society of Japan, erschienen am 15.06.2025. Verfasst von Ichiro Ohta und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 21 Literaturangaben. Gefördert von: Japan Science and Technology Agency.
Abstract (Originalsprache)
In recent years, there has been a growing interest in data-driven approaches in physics, such as extended dynamic mode decomposition (EDMD). The EDMD algorithm focuses on nonlinear time-evolution systems, and the constructed Koopman matrix yields the next-time prediction with only linear matrix-product operations. Note that data-driven approaches generally require a large dataset. However, assume that one has some prior knowledge, even if it may be ambiguous. Then, one could achieve sufficient learning from only a small dataset by taking advantage of the prior knowledge. This paper yields methods for incorporating ambiguous prior knowledge into the EDMD algorithm. The ambiguous prior knowledge in this paper corresponds to the underlying time-evolution equations with unknown parameters. First, we apply the proposed method to forward problems, i.e., prediction tasks. Second, we propose a scheme to apply the proposed method to inverse problems, i.e., parameter estimation tasks. We demonstrate the learning with only a small dataset using guiding examples, i.e., the Duffing and the van der Pol systems.
Förderung
- Japan Science and Technology Agency
Zitieren
APA
Ohta, I., Koyanagi, S., Kinjo, K., & Ohkubo, J. (2025). Integrated Utilization of Equations and Small Dataset in the Koopman Operator: Applications to Forward and Inverse Problems. Journal of the Physical Society of Japan, 94(6). https://doi.org/10.7566/jpsj.94.064001
Vancouver
Ohta I, Koyanagi S, Kinjo K, Ohkubo J. Integrated Utilization of Equations and Small Dataset in the Koopman Operator: Applications to Forward and Inverse Problems. Journal of the Physical Society of Japan. 2025;94(6). doi:10.7566/jpsj.94.064001
BibTeX
@article{Ohta2025,
author = {Ohta, Ichiro and Koyanagi, Shota and Kinjo, Kayo and Ohkubo, Jun},
title = {Integrated Utilization of Equations and Small Dataset in the Koopman Operator: Applications to Forward and Inverse Problems},
journal = {Journal of the Physical Society of Japan},
year = {2025},
volume = {94},
number = {6},
doi = {10.7566/jpsj.94.064001}
}
EUVIMED