Chaztikov's repositories
PINN_Quadrature
Studying quadrature methods applied to PINNs
Conservative_PINNs
We propose a conservative physics-informed neural network (cPINN) on decompose domains for nonlinear conservation laws. The conservation property of cPINN is obtained by enforcing the flux continuity in the strong form along the sub-domain interfaces.
DeepPDELearner
This repository introduces Partial Differential Equation Solver using neural network that can learn resolution-invariant solution operators on Navier-Stokes equation. Solving PDE is the core subject of numerical simulation and is widely used in science and engineering, from molecular dynamics to flight simulation, and even weather forecasting.
hpinn
hPINN: Physics-informed neural networks with hard constraints
TensorDiffEq
Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing
A-PINN
A-PINN: Auxiliary physics informed neural networks for forward and inverse problems of nonlinear integro-differential equations
EP-PINNs
EP-PINNs implementation for 1D and 2D forward and inverse solvers for the Aliev-Panfilov cardiac electrophysiology model. Also includes Matlab finite-differences solver for data generation.
gptorch
Gaussian processes with PyTorch
Neural-Network-for-solving-PDE
Different methods of solving partial differential equations with neural networks
idrlnet
IDRLnet, a Python toolbox for modeling and solving problems through Physics-Informed Neural Network (PINN) systematically.
SA-PINNs
Implementation of the paper "Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism" [AAAI-MLPS 2021]
NeuralPDE.jl
Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
IB2d
An easy to use immersed boundary method in 2D, with full implementations in MATLAB and Python that contains over 60 built-in examples, including multiple options for fiber-structure models and advection-diffusion, Boussinesq approximations, and/or artificial forcing.
Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics
Using Physics-Informed Deep Learning (PIDL) techniques (W-PINNs-DE & W-PINNs) to solve forward and inverse hydrodynamic shock-tube problems and plane stress linear elasticity boundary value problems
UQPINNs-TF2.0
TensorFlow 2.0 implementation of Yibo Yang, Paris Perdikaris’s adversarial Uncertainty Quantification in Physics Informed Neural Networks (UQPINNs).
examples
Chebfun examples collection
Physics-Informed-Neural-Networks
Investigating PINNs
spectralDNS
Spectral Navier Stokes (and similar) solvers in Python
sciann-applications
A place to share problems solved with SciANN
FwdInvToolkit
Forward/Inverse Toolkit
ngboost
Natural Gradient Boosting for Probabilistic Prediction