aiqbench analysis
CraftSPH introduces a modular, differentiable framework for Smoothed Particle Hydrodynamics (SPH) built on PyTorch, enabling seamless integration of high-accuracy numerical schemes with deep learning models. By supporting automatic differentiation across explicit and implicit computations, this tool facilitates advanced applications in physical parameter estimation and fluid dynamics optimization. It represents a significant step toward unifying classical computational physics with modern machine learning architectures for solving complex deformation problems.
CraftSPH: A high-accuracy and composable differentiable SPH solver implemented in PyTorch
arXiv:2609.38208v1 Announce Type: cross Abstract: Smoothed Particle Hydrodynamics (SPH) is well suited to a range of problems, particularly those involving large deformations in fluid dynamics. In recent years, in addition to the advancement of SPH formulations, the development of differentiable solvers has also progressed. However, unified frameworks that flexibly accommodate diverse numerical schemes, including advanced and implicit methods, while supporting continuous extension and updating remain limited. In this study, a high-accuracy and composable differentiable SPH solver, CraftSPH, has been developed. In CraftSPH, major computational operations are implemented as independent modules, which can be combined according to the intended purpose of constructing a solver. This design enables different computational schemes to be intuitively constructed from combinations of common components and allows newly developed high-accuracy discretization methods to be flexibly incorporated and extended. Furthermore, each module supports automatic differentiation, enabling applications to physical-parameter estimation and to optimization that combines SPH solvers with deep learning models. Accordingly, CraftSPH provides an SPH computational framework in which high-accuracy discretization, explicit and implicit computations, and automatic differentiation can be handled in a unified and extensible manner. To demonstrate the applicability of CraftSPH to a wide range of problems, forward analyses are conducted for Poiseuille flow, two- and three-dimensional dam-break problems, and a rising-bubble problem. In addition, the performance of automatic differentiation is evaluated through inverse problems involving parameter estimation for the Taylor-Green vortex and lid-driven cavity flow.
Abstract:Smoothed Particle Hydrodynamics (SPH) is well suited to a range of problems, particularly those involving large deformations in fluid dynamics. In recent years, in addition to the advancement of SPH formulations, the development of differentiable solvers has also progressed. However, unified frameworks that flexibly accommodate diverse numerical schemes, including advanced and implicit methods, while supporting continuous extension and updating remain limited. In this study, a high-accuracy and composable differentiable SPH solver, CraftSPH, has been developed. In CraftSPH, major computational operations are implemented as independent modules, which can be combined according to the intended purpose of constructing a solver. This design enables different computational schemes to be intuitively constructed from combinations of common components and allows newly developed high-accuracy discretization methods to be flexibly incorporated and extended. Furthermore, each module supports automatic differentiation, enabling applications to physical-parameter estimation and to optimization that combines SPH solvers with deep learning models. Accordingly, CraftSPH provides an SPH computational framework in which high-accuracy discretization, explicit and implicit computations, and automatic differentiation can be handled in a unified and extensible manner. To demonstrate the applicability of CraftSPH to a wide range of problems, forward analyses are conducted for Poiseuille flow, two- and three-dimensional dam-break problems, and a rising-bubble problem. In addition, the performance of automatic differentiation is evaluated through inverse problems involving parameter estimation for the Taylor-Green vortex and lid-driven cavity flow.
Fluid Dynamics (physics.flu-dyn); Machine Learning (cs.LG); Numerical Analysis (math.NA)
arXiv:2609.38208 [physics.flu-dyn]
(or arXiv:2609.38208v1 [physics.flu-dyn] for this version)
https://doi.org/10.48550/arXiv.2609.38208 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 324 words
