Stars
High‑performance multiphysics CFD framework for turbulent reacting multiphase flows from low to high Mach number
Large-scale Time-series Dataset Towards Next-Generation Global Station Weather Forecasting Benchmark
This project contains a simulation framework for leveraging deep reinforcement learning in studying of the fluid dynamics. Stable BaseLine 3 and WaterLily are essential.
Weak SINDy model discovery for atmospheric data.
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
United collection of hybrid Central solvers - one-phase, two-phase and multicomponent versions
Official implementation of Diffusion Graph Networks (DGNs)
Code for the paper "Generative AI for fast and accurate statistical computation of fluids"
A tutorial showcasing the process of scaling up a SciML algorithm for multi-node training
Data-driven Reynolds-averaged turbulence modeling with generalizable non-linear correction and uncertainty quantification using Bayesian deep learning
Accelerated fulid-structure interaction (FSI) simulation using immersed boundary lattice Boltzmann method (IB-LBM) powered by JAX.
Control of Hypersonic Shock-Wave/Laminar Boundary-Layer Interaction using Deep Reinforcement Learning
Generalizing CNNs to Graphs with Learnable Neighborhood Quantization
[CVPR 2025 Oral] Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
Implementation of the Prithvi WxC Foundation Model and Downstream Tasks
Software for training, running and analyzing a Deep Learning Earth System Model (DLESyM)
PyTorch implementation of DANN (Domain-Adversarial Training of Neural Networks)
A fully-differentiable compressible reacting flow solver based on JAX-AMR
Differentiable interface to FEniCS/Firedrake for JAX using dolfin-adjoint/pyadjoint
A Python implementation of multifidelity Monte Carlo estimation
Implementation of all RL algorithms in a simpler way
PDEBench: An Extensive Benchmark for Scientific Machine Learning