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'.

Datasets and code for results presented in the BOON paper

Code for training and inferring acoustic wave propagation in 3D

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

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

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

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

Graph Feedforward Networks: a resolution-invariant generalisation of feedforward networks for graphical data, applied to model order reduction

Nonlinear model reduction for operator learning

Benchmarking Surrogates for coupled ODE systems.

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

Hyperbolic Learning Rate Scheduler

Project Portfolio

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

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

Training Distribution Selection for Provable OOD Performance

Fokker Planck based Data Assimilation method using Fourier Neural Operators as integrator

Code required to reproduce results presented in "Probabilistic Operator Learning for Climate Model Parameterisation"