yriyazi/Koopman-Operator-and-Deep-Neural-Networks-ISAV2023

In this work, we present a novel approach that combines the power of Koopman operators and deep neural networks to generate a linear representation of the Duffing oscillator. This approach enables effective parameter estimation and accurate prediction of the oscillator's future behavior.

41
/ 100
Emerging

This project helps researchers and engineers analyze and predict the behavior of complex Duffing oscillators. It takes time-series data of oscillator movement and uses a combination of advanced mathematical techniques and deep learning to estimate system parameters and forecast future states. The primary users are researchers in physics, engineering, or mathematics who study nonlinear dynamics.

Use this if you need to perform in-depth parameter estimation, long-term prediction, and qualitative analysis of Duffing oscillators using state-of-the-art methods.

Not ideal if you are dealing with a different type of nonlinear system or require a straightforward, off-the-shelf solution for general time-series forecasting without deep dynamical insights.

nonlinear-dynamics vibration-analysis dynamical-systems mathematical-modeling system-identification
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

10

Forks

3

Language

Jupyter Notebook

License

Last pushed

Dec 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yriyazi/Koopman-Operator-and-Deep-Neural-Networks-ISAV2023"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.