lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
Implements physics-informed neural networks (PINNs), DeepONet operators, and multifidelity learning to solve forward/inverse differential equations and learn solution operators without explicit meshing. Supports five interchangeable tensor backends (TensorFlow, PyTorch, JAX, PaddlePaddle) and provides domain geometry handling through constructive solid geometry, multiple boundary condition types, and adaptive sampling strategies to improve accuracy.
3,954 stars. Used by 1 other package. Available on PyPI.
Stars
3,954
Forks
936
Language
Python
License
LGPL-2.1
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Dependencies
5
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lululxvi/deepxde"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
patrick-kidger/torchcde
Differentiable controlled differential equation solvers for PyTorch with GPU support and...