PyTorch implementation of the diffusion-based method for CFD data super-resolution proposed in the paper "A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction".

Deep renormalized Mori-Zwanzig (DrMZ) Julia package.

A benchmark library for DRL-based flow control

Benchmarking of diffusion models for global field reconstruction from sparse observations

Exercises and notes for N.G. Van Kampen's Stochastic Processes in Physics and Chemistry

Large-Scale Multimodal Dataset of Astronomical Data

A 15TB Collection of Physics Simulation Datasets

AL4PDE: A Benchmark for Active Learning for Neural PDE Solvers

Simulation-based inference in JAX

Finite difference tools in JAX

A code for fast, massively-parallel of two-phase flows with heat transfer

Simple and easily configurable grid world environments for reinforcement learning

Posterior Sampling using Latent Diffusion

Stochastic Normalizing Flows

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Matrix-free linear algebra in JAX.

Probabilistic Programming and Nested sampling in JAX

Geophysical fluid dynamics pseudospectral solvers with Julia and FourierFlows.jl.

Differentiable QP solver in JAX

Special functions in Jax

An Extensible Deep Learning Library

A user-friendly framework for building GPU-accelerated spectral simulations of 2-dimensional computational fluid dynamics problems.

Fully and Partially Bayesian Neural Nets

Orthogonal polynomials with JAX

Machine learning algorithms for discovering dimensionless groups from simulation and experimental data

Starting codes for the 2022-05-26 DiRAC Cluster Challenge

[Neurips 2024] A benchmark suite for autoregressive neural emulation of PDEs. (≥46 PDEs in 1D, 2D, 3D; Differentiable Physics; Unrolled Training; Rollout Metrics)

Efficient Differentiable n-d PDE solvers in JAX.