Saved in:
Bibliographic Details
Main Authors: Ramos-Osuna, Víctor, Díaz-Álvarez, Alberto, Lara-Cabrera, Raúl
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.01169
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912305855332352
author Ramos-Osuna, Víctor
Díaz-Álvarez, Alberto
Lara-Cabrera, Raúl
author_facet Ramos-Osuna, Víctor
Díaz-Álvarez, Alberto
Lara-Cabrera, Raúl
contents This paper presents a novel approach for accelerating n-body simulations by integrating a physics-informed graph neural networks (GNN) with traditional numerical methods. Our method implements a leapfrog-based simulation engine to generate datasets from diverse astrophysical scenarios which are then transformed into graph representations. A custom-designed GNN is trained to predict particle accelerations with high precision. Experiments, conducted on 60 training and 6 testing simulations spanning from 3 to 500 bodies over 1000 time steps, demonstrate that the proposed model achieves extremely low prediction errors-loss values while maintaining robust long-term stability, with accumulated errors in position, velocity, and acceleration remaining insignificant. Furthermore, our method yields a modest speedup of approximately 17% over conventional simulation techniques. These results indicate that the integration of deep learning with traditional physical simulation methods offers a promising pathway to significantly enhance computational efficiency without compromising accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01169
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient n-body simulations using physics informed graph neural networks
Ramos-Osuna, Víctor
Díaz-Álvarez, Alberto
Lara-Cabrera, Raúl
Machine Learning
Computational Physics
This paper presents a novel approach for accelerating n-body simulations by integrating a physics-informed graph neural networks (GNN) with traditional numerical methods. Our method implements a leapfrog-based simulation engine to generate datasets from diverse astrophysical scenarios which are then transformed into graph representations. A custom-designed GNN is trained to predict particle accelerations with high precision. Experiments, conducted on 60 training and 6 testing simulations spanning from 3 to 500 bodies over 1000 time steps, demonstrate that the proposed model achieves extremely low prediction errors-loss values while maintaining robust long-term stability, with accumulated errors in position, velocity, and acceleration remaining insignificant. Furthermore, our method yields a modest speedup of approximately 17% over conventional simulation techniques. These results indicate that the integration of deep learning with traditional physical simulation methods offers a promising pathway to significantly enhance computational efficiency without compromising accuracy.
title Efficient n-body simulations using physics informed graph neural networks
topic Machine Learning
Computational Physics
url https://arxiv.org/abs/2504.01169