Benutzer: Gast  Login
Titel:

JAX-SPH: A Differentiable Smoothed Particle Hydrodynamics Framework

Dokumenttyp:
Konferenzbeitrag
Art des Konferenzbeitrags:
Textbeitrag / Aufsatz
Autor(en):
Toshev, Artur; Ramachandran, Harish; Erbesdobler, Jonas A.; Galletti, Gianluca; Brandstetter, Johannes; Adams, Nikolaus A.
Abstract:
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 H...     »
Stichworte:
Smoothed Particle Hydrodynamics, JAX, Lagrangian Simulations, Differentiable Solver
Dewey-Dezimalklassifikation:
620 Ingenieurwissenschaften
Kongress- / Buchtitel:
ICLR 2024 Workshop on AI4DifferentialEquations In Science
Jahr:
2024
Sprache:
en
WWW:
https://openreview.net/forum?id=8X5PXVmsHW
TUM Einrichtung:
Lehrstuhl für Aerodynamik und Strömungsmechanik
 BibTeX