nbouziani/physics-driven-ml
Physics-driven machine learning using PyTorch and Firedrake
This project helps researchers and engineers who work with physics-based simulations by generating data and training machine learning models that integrate directly with partial differential equations (PDEs). It takes parameters for physical systems and observed data, then produces trained machine learning models capable of solving inverse problems like inferring material properties. The end-users are computational scientists, physicists, and engineers working on complex simulation and modeling tasks.
No commits in the last 6 months.
Use this if you need to build and evaluate machine learning models that are deeply coupled with physics simulations described by partial differential equations, especially for inverse problems.
Not ideal if your problem doesn't involve complex physics simulations or if you are not comfortable working with Python and scientific computing environments like Firedrake and PyTorch.
Stars
16
Forks
11
Language
Python
License
MIT
Category
Last pushed
Jan 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nbouziani/physics-driven-ml"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SciML/NeuralPDE.jl
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for...
NVIDIA/physicsnemo
Open-source deep-learning framework for building, training, and fine-tuning deep learning models...
NVIDIA/physicsnemo-sym
Framework providing pythonic APIs, algorithms and utilities to be used with PhysicsNeMo core to...
idrl-lab/idrlnet
IDRLnet, a Python toolbox for modeling and solving problems through Physics-Informed Neural...
mathLab/PINA
Physics-Informed Neural networks for Advanced modeling