mlsanityData to 7 Oct 2026

JAX-SPH: A Differentiable Smoothed Particle Hydrodynamics Framework

arXiv 2403.04750 ↗First posted 7 Mar 2024physics.flu-dyn cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Particle-based fluid simulations have emerged as a powerful tool for solving the Navier-Stokes equations, especially in cases that include intricate physics and free surfaces. The recent addition of machine learning methods to the toolbox for solving such problems is pushing the boundary of the quality vs. speed tradeoff of such numerical simulations. In this work, we lead the way to Lagrangian fluid simulators compatible with deep learning frameworks, and propose JAX-SPH - a Smoothed Particle Hydrodynamics (SPH) framework implemented in JAX. JAX-SPH builds on the code for dataset generation from the LagrangeBench project (Toshev et al., 2023) and extends this code in multiple ways: (a) integration of further key SPH algorithms, (b) restructuring the code toward a Python package, (c) verification of the gradients through the solver, and (d) demonstration of the utility of the gradients for solving inverse problems as well as a Solver-in-the-Loop application. Our code is available at https://github.com/tumaer/jax-sph.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 19 of its 48 references that are in the map. First posted on arXiv 7 Mar 2024.

Builds on

19 of 48 references.

References · 19

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  3. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  4. 2021Machine learning accelerated computational fluid dynamicscited by 461
  5. 2022On Neural Differential Equationscited by 264
  6. 2020Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solverscited by 201
  7. 2020Learning to Control PDEs with Differentiable Physicscited by 131
  8. 2022Physics-informed neural networks for inverse problems in supersonic flowscited by 75
  9. 2021Physics-based Deep Learningcited by 67
  10. 2018SPNets: Differentiable Fluid Dynamics for Deep Neural Networkscited by 62
  11. 2022JAX-FLUIDS: A fully-differentiable high-order computational fluid dynamics solver for compressible two-phase flowscited by 36
  12. 2022Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networkscited by 33
7 more
  1. 2023LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suitecited by 26
  2. 2021Composing Partial Differential Equations with Physics-Aware Neural Networkscited by 21
  3. 2023Machine Learning for Partial Differential Equationscited by 20
  4. 2023Learning Lagrangian Fluid Mechanics with E(3)-Equivariant Graph Neural Networkscited by 12
  5. 2024Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamicscited by 10
  6. 2020Smoothed Particle Hydrodynamics Techniques for the Physics Based Simulation of Fluids and Solidscited by 9
  7. 2023On the Relationships between Graph Neural Networks for the Simulation of Physical Systems and Classical Numerical Methodscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025SIMSHIFT: A Benchmark for Adapting Neural Surrogates to Distribution Shiftscited by 6
  2. 2026Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statisticscited by 0
  3. 2026CraftSPH: A high-accuracy and composable differentiable SPH solver implemented in PyTorchcited by 0