# PyDMD/PyDMD

Python Dynamic Mode Decomposition

Repository: https://github.com/PyDMD/PyDMD
Canonical: https://ross.abutalabs.com/products/pydmd
Homepage: https://pydmd.github.io/PyDMD/
Language: Python
License: MIT
License Family: permissive
Topics: dynamic-mode-decomposition, dmd, mrdmd, hodmd, data-driven, python, numfocus, model-order-reduction, scientific-machine-learning
Last push: 2025-12-19T16:34:30+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 58, release rhythm 41, longevity 100
- inputs: {"age_days": 3369, "days_push": 257, "days_rel": 397, "gap_med": 30, "n_releases_24m": 10}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1251, forks 357 (observed 2026-08-28T04:04:08.194036+00:00)

## What it is
PyDMD is a Python package implementing Dynamic Mode Decomposition (DMD) and its many variants (mrDMD, HODMD, etc.) for extracting spatiotemporal coherent structures from time-varying data. It integrates with NumPy/SciPy and offers visualization tools for mode reconstruction, energy spectra, and time evolution.

## Use cases
- decompose time-varying simulation data into spatial and temporal modes
- perform model order reduction on high-dimensional dynamical systems
- analyze fluid dynamics flows for coherent structures
- extract dominant modes from noisy or large datasets
- apply DMD with control variables or imposed physical structure
- reconstruct and visualize the temporal evolution of system dynamics

## When to choose
- you need data-driven decomposition of spatiotemporal datasets in Python
- you want access to many DMD variants (mrDMD, HODMD, forward-backward, etc.) in one package
- you work in the scientific Python ecosystem with NumPy/SciPy
- you need a well-documented, actively maintained, NumPy-affiliated research library

## When to avoid
- you need real-time streaming decomposition rather than offline analysis
- your problem is standard time-series forecasting better served by ARIMA or deep learning models
- you require GPU-accelerated or distributed computation out of the box
- you need a GUI-based analysis tool rather than a Python API

## Facets
- artifact type: library
- maturity: active
- function: data-science, machine-learning, math, simulation
- domain: data-science, machine-learning
- platform: python, cross-platform
- tags: dynamic-mode-decomposition, dmd, model-order-reduction, scientific-machine-learning, numfocus, time-series-analysis, fluid-dynamics, algorithms, scientific-computing

## Member repositories
- PyDMD/PyDMD (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:08.194036+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:07:37.311511+00:00, confidence not recorded.
  - readme: https://github.com/PyDMD/PyDMD (fetched 2026-08-28T04:04:08.194036+00:00, sha 9b7e31531c68)
  - homepage: https://pydmd.github.io/PyDMD/ (fetched 2026-08-29T12:18:33.976942+00:00, sha 7f242c2efdcf)
  - registry_pypi: https://pypi.org/pypi/pydmd/json (fetched 2026-08-29T12:18:34.010123+00:00, sha 4bf58693dca4)
- Data as of 2026-08-30T08:39:29.467469+00:00.