Scientific Machine Learning Python Packages

pydmd

Python Dynamic Mode Decomposition

tesseract-core

Universal components for differentiable scientific computing. :package:

pinnforge

Solve PDEs in 3 lines of code: Physics-Informed Neural Networks made easy

deepxde

A library for scientific machine learning and physics-informed learning

jaxns

Probabilistic Programming and Nested sampling in JAX

tesseract-jax

Execute + differentiate Tesseracts as part of JAX programs, with full support for function transformations like JIT, grad, and more. ⚡

causal-hybrid-control

Physics-structured dynamics with a learned causal residual, controlled by constrained optimal control / MPC.

bibr

Modern scientific extraction pipeline

pinnstudio

A No-Code Scientific Computing Environment for Forward and Inverse Physics-Informed Neural Networks

mestra

An open data format for parametric and time-dependent simulation data and surrogate models. Spec, conformance corpus, and readers and writers for Python, MATLAB, Julia, and C++.

opinf

Operator Inference for data-driven, non-intrusive model reduction of dynamical systems.

diffeqpy

Solving differential equations in Python using DifferentialEquations.jl and the SciML Scientific Machine Learning organization

nefi

Neural-field inversion: recover hidden physical fields from a single measurement with differentiable physics and no training data

pyplaid

PLAID (Physics-Learning AI Datamodel), a flexible and extensible framework for representing and sharing datasets of physics simulations

jax-numerical-operators

Differentiable numerical solvers and scientific machine learning on one JAX substrate; you write the math, it stays differentiable end to end.

tesseract-torch

Execute + differentiate Tesseracts as part of PyTorch programs, with full support for reverse-mode and forward-mode AD. 🔦

lirisimpact

Repository contaning the original code of IMPACT algorithm, an interpretable model for ordinal predictions with multi-class outputs"

robustsignalmaker

NaN-aware, leakage-free stability selection for scientific signals and spectra

adcd

Discover physical correction laws from anomalous data in JAX.

jwave

A JAX-based research framework for differentiable and parallelizable acoustic simulations, on CPU, GPUs and TPUs

phaethon

End-to-End Physics-Constrained Scientific Computing & Sci-ML Framework

tensordiffeq

Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing

rom-operator-inference

Operator Inference for data-driven, non-intrusive model reduction of dynamical systems.

pinnlab

A comprehensive, production-ready PyTorch implementation of Physics-Informed Neural Networks for solving partial differential equations (PDEs). This repository provides modular implementations with advanced visualization, comprehensive error analysis, and state-of-the-art sampling strategies.