DyMAD: Dynamics Modeling and Analysis with Data

Version 0.1 as of 07/13/25: Code; Documentation.

DyMAD aims to provide a lightweight and user-friendly toolkit for modeling and analyzing dynamical systems using data-driven approaches.

Currently, we have implemented the following features:

• Data preprocessing pipeline specialized for time series data.
• Models for different types of dynamical systems, including
  • Latent Dynamics Models
  • Koopman Bilinear Forms
  • The graph version of the above
• Training utilities, including
  • Neural-ODE-based optimizer
  • Weak-form optimizer
• Miscellaneous utilities, including
  • Samplers for inputs and initial conditions
  • Visualization tools

The implemented and planned algorithms and features for DyMAD are mainly based on the research work from our lab. The lead developer is Dr. Yin Yu, whose PhD thesis is on the topic of data-driven modeling of dynamical systems on graphs.

It is still far from complete, see our Roadmap for more details.

Feel free to try it out, give feedback, and/or contribute!