PaddleScience is SDK and library for developing AI-driven scientific computing applications based on PaddlePaddle.

Source code of 'Deep transfer operator learning for partial differential equations under conditional shift'.

Code for training and inferring acoustic wave propagation in 3D

Datasets and code for results presented in the BOON paper

Official repo for separable operator networks -- extreme-scale operator learning for parametric PDEs.

PyTorch implemention of the Position-induced Transformer for operator learning in partial differential equations

Folax (Finite Operator Learning with JAX) is a framework for solving and optimizing PDEs by integrating machine learning with numerical methods in computational mechanics.

An extension of Fourier Neural Operator to finite-dimensional input and/or output spaces.

TANTE: Time-Adaptive Operator Learning via Neural Taylor Expansion

Code for the paper "The Random Feature Model for Input-Output Maps between Banach Spaces" (SIREV SIGEST 2024, SISC 2021)

Official implementation of the paper "Neural Hamilton: Can A.I. Understand Hamiltonian Mechanics?"

Graph Feedforward Network (GFN) - a novel neural network layer for resolution-invariant machine learning

Nonlinear model reduction for operator learning

Benchmarking Surrogates for coupled ODE systems.

Bridging infinite-dimensional delay dynamics with fully GPU-accelerated finite-dimensional Koopman learning and provable error bounds for nonlinear delay-differential equations.

CHONKNORIS: Operator Learning at Machine Precision

DMD Neural Operator - A neural operator using DMD analysis to approximate the PDEs

Code for the paper ``Error Bounds for Learning with Vector-Valued Random Features'' (NeurIPS 2023, Spotlight)

Data generation from PDEs for training ML/AI models with UQ

Hyperbolic Learning Rate Scheduler