Latent Diffeomorphic Dynamic Mode Decomposition

Willem Diepeveen, Jon Schwenk, Andrea Bertozzi
5/9/2025
cs.LGmath.DS

No official code found. Best implementation: wdiepeveen/Latent-Diffeomorphic-Dynamic-Mode-Decomposition (0 stars, GPL-3.0, last commit 2025-05-13).

Abstract

We present Latent Diffeomorphic Dynamic Mode Decomposition (LDDMD), a new data reduction approach for the analysis of non-linear systems that combines the interpretability of Dynamic Mode Decomposition (DMD) with the predictive power of Recurrent Neural Networks (RNNs). Notably, LDDMD maintains simplicity, which enhances interpretability, while effectively modeling and learning complex non-linear systems with memory, enabling accurate predictions. This is exemplified by its successful application in streamflow prediction.

View on arXivView PDF

Code Implementations(1)

wdiepeveen/Latent-Diffeomorphic-Dynamic-Mode-DecompositionCommunity100%
GPL-3.0
00Python, Jupyter NotebookApr 2, 20251 years agoGPL-3.0

Similar Papers

A Neural Operator based on Dynamic Mode Decomposition

82% match2025

Machine Learning Enhanced Hankel Dynamic-Mode Decomposition

80% match2023

Representing Neural Network Layers as Linear Operations via Koopman Operator Theory

80% match2024

RRAEDy: Adaptive Latent Linearization of Nonlinear Dynamical Systems

80% match1 repo12025

Neural Ordinary Differential Equations for Learning and Extrapolating System Dynamics Across Bifurcations

80% match2025

Latent Dynamics Networks (LDNets): learning the intrinsic dynamics of spatio-temporal processes

79% match2023

Cite this paper

@article{diepeveen2025latent,
  title  = {Latent Diffeomorphic Dynamic Mode Decomposition},
  author = {Willem Diepeveen and Jon Schwenk and Andrea Bertozzi},
  year   = {2025},
  eprint = {2505.06351},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.06351v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.06351.svg)](https://codeofpaper.com/paper/2505.06351)

Discussion