CraftSPH: A composable framework for differentiable smoothed particle hydrodynamics implemented in PyTorch
Abstract
Smoothed particle hydrodynamics (SPH) is well suited to large-deformation fluid problems, and the growing use of automatic differentiation in engineering applications has motivated interest in differentiable SPH solvers. In this study, a composable differentiable SPH framework, CraftSPH, has been developed. In CraftSPH, major computational operations are implemented as independent modules that users can combine to construct solvers for different purposes. This design supports high-accuracy discretization and both explicit and implicit computation within a common framework, while allowing individual components to be maintained and extended. Selected numerical operations also support automatic differentiation (AD) for physical-parameter estimation and potential coupling with deep learning models. These capabilities were demonstrated through forward and inverse analyses. Forward analyses using an implicit SPH scheme with high-accuracy discretization showed good agreement with analytical and reference solutions for Poiseuille flow and a rising bubble, while capturing the key experimental trends in two- and three-dimensional dam-break problems. In inverse analyses, explicit and implicit SPH schemes were used to estimate kinematic viscosity in Taylor-Green vortex flow and Reynolds number in lid-driven cavity flow. The results also showed that the choice of operations included in the computational graph affects the computed gradients. Together, these findings demonstrate that CraftSPH enables users to assemble problem-specific solvers for forward and inverse analyses within a common framework.
Related
- JAXIGA - A software framework for GPU-enabled and differentiable isogeometric analysis
- KernelPack-JAX: a meshless differentiable GPU framework for node generation and forward and inverse PDE problems
- DeepTelecom: A Differentiable Multimodal Framework for Channel Twinning in Dynamic Heterogeneous Wireless Environments
- Peak-Weighted Calibration of Implemented Integer-Order, Caputo, and Atangana–Baleanu–Caputo Schemes for Simultaneous COVID-19 and Influenza Transmission
- Walk on Multiscale Media: Compiling Editable and Composable Transport Medium Prefabs for Monte Carlo PDE Solvers
BibTeX
@misc{matono2026craftsph,
title = {{CraftSPH: A composable framework for differentiable smoothed particle hydrodynamics implemented in PyTorch}},
author = {Gen Matono and Shujiro Fujioka and Mayuko Nishio},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.38208},
eprint = {2609.38208},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.38208},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - CraftSPH: A composable framework for differentiable smoothed particle hydrodynamics implemented in PyTorch
AU - Gen Matono
AU - Shujiro Fujioka
AU - Mayuko Nishio
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2609.38208
UR - https://arxiv.org/abs/2609.38208
AB - Smoothed particle hydrodynamics (SPH) is well suited to large-deformation fluid problems, and the growing use of automatic differentiation in engineering applications has motivated interest in differentiable SPH solvers. In this study, a composable differentiable SPH framework, CraftSPH, has been developed. In CraftSPH, major computational operations are implemented as independent modules that users can combine to construct solvers for different purposes. This design supports high-accuracy discretization and both explicit and implicit computation within a common framework, while allowing individual components to be maintained and extended. Selected numerical operations also support automatic differentiation (AD) for physical-parameter estimation and potential coupling with deep learning models. These capabilities were demonstrated through forward and inverse analyses. Forward analyses using an implicit SPH scheme with high-accuracy discretization showed good agreement with analytical and reference solutions for Poiseuille flow and a rising bubble, while capturing the key experimental trends in two- and three-dimensional dam-break problems. In inverse analyses, explicit and implicit SPH schemes were used to estimate kinematic viscosity in Taylor-Green vortex flow and Reynolds number in lid-driven cavity flow. The results also showed that the choice of operations included in the computational graph affects the computed gradients. Together, these findings demonstrate that CraftSPH enables users to assemble problem-specific solvers for forward and inverse analyses within a common framework.
ER -