PDEBench: An Extensive Benchmark for Scientific Machine Learning

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

Implementation of the paper "Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism" [AAAI-MLPS 2021]

Official PyTorch implementation of PTS/PSRN: Fast and efficient symbolic expression discovery through parallelized tree search. Evaluates millions of expressions simultaneously on GPU with automated subtree reuse.

A set of tools for developing new methods and techniques in physics informed neural networks written in jax.

Learnable Orthogonal Decomposition for Non-Regressive Prediction for PDE

Final projects for 401-4656-21L AI in Sciences and Engineering @ ETHz. Includes implementation of Fourier Neural Operator (FNO) with time dependency, data-driven symbolic regression with PDE-Find and foundation model based on FNO for phase-field dynamics