# dynamicslab/pysindy

A package for the sparse identification of nonlinear dynamical systems from data

Repository: https://github.com/dynamicslab/pysindy
Canonical: https://ross.abutalabs.com/products/pysindy
Homepage: https://pysindy.readthedocs.io/en/latest/
Language: Python
License: NOASSERTION
License Family: other
Topics: dynamical-systems, machine-learning, sparse-regression, model-discovery, system-identification, nonlinear-dynamics
Last push: 2026-06-10T21:36:54+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 41, longevity 100
- inputs: {"age_days": 2672, "days_push": 84, "days_rel": 237, "gap_med": 139, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1893, forks 384 (observed 2026-08-28T04:05:50.586906+00:00)

## What it is
PySINDy is a Python library for discovering governing equations of dynamical systems from measurement data using the Sparse Identification of Nonlinear Dynamical systems (SINDy) method and related sparse regression techniques. The resulting models are interpretable symbolic equations that can be used for prediction, control, and theoretical analysis.

## Use cases
- discover differential equations from time-series data
- fit sparse regression models to identify nonlinear dynamics
- infer governing equations of a physical system from measurements
- build interpretable models of dynamical systems for prediction and control
- perform system identification on experimental or simulation data
- learn symbolic equations of motion from trajectory data

## When to choose
- you have time-series measurements and want interpretable symbolic equations rather than a black-box model
- you need to identify sparse nonlinear dynamics with techniques like SR3, MIOSR, or Bayesian regression
- you want a well-documented, actively maintained scientific Python package with tutorials

## When to avoid
- you need black-box forecasting accuracy rather than interpretable equations
- your data is noisy, sparse, or lacks the sampling quality SINDy methods require
- you need a general-purpose deep learning time-series model instead of equation discovery

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, data-science, simulation, math
- domain: machine-learning, data-science, simulation
- platform: python, cross-platform
- tags: system-identification, sparse-regression, dynamical-systems, model-discovery, nonlinear-dynamics, interpretable-models, scientific-computing, algorithms

## Member repositories
- dynamicslab/pysindy (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:50.586906+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 2026-08-30T03:12:55.536747+00:00, confidence not recorded.
  - readme: https://github.com/dynamicslab/pysindy (fetched 2026-08-28T04:05:50.586906+00:00, sha c9d0121b8d5c)
- Data as of 2026-08-30T08:39:29.467469+00:00.