PySHRED (Legacy Version)

⚠️ Warning: This is the legacy version of PySHRED.

Development and maintenance have moved to the actively maintained repository:
PySHRED (current)

This version is no longer maintained and is preserved for archival purposes.

Overview

PySHRED: A Python Package for SHallow REcurrent Decoders (SHRED) for Spatial-Temporal Systems

1. Install from Source

To install PySHRED manually, follow these steps.

git clone https://github.com/PyShred-Dev/PySHRED.git
cd pyshred-legacy
pip install .

Note: Installation may take slightly longer than usual since example SST data in included. All dataset will be moved onto Zenodo once PySHRED is officially released.

2. Install from PyPI (Coming Soon!)

PySHRED will soon be officially released on PyPI.

Documentation (Coming Soon!)

Examples and Tutorials:

• SST Tutorial
• More examples in the examples/ directory (coming soon)

References

[1] Jan P. Williams, Olivia Zahn, and J. Nathan Kutz, "Sensing with shallow recurrent decoder networks", arXiv:2301.12011, 2024. Read on arXiv

[2] M.R. Ebers, J.P. Williams, K.M. Steele, and J.N. Kutz, "Leveraging Arbitrary Mobile Sensor Trajectories With Shallow Recurrent Decoder Networks for Full-State Reconstruction," IEEE Access, vol. 12, pp. 97428-97439, 2024. doi: 10.1109/ACCESS.2024.3423679. Read on IEEE

[3] J. Nathan Kutz, Maryam Reza, Farbod Faraji, and Aaron Knoll, "Shallow Recurrent Decoder for Reduced Order Modeling of Plasma Dynamics", arXiv:2405.11955, 2024. Read on arXiv

[4] Mars Liyao Gao, Jan P. Williams, and J. Nathan Kutz, "Sparse Identification of Nonlinear Dynamics and Koopman Operators with Shallow Recurrent Decoder Networks", arXiv:2501.13329, 2025. Read on arXiv