<ul><li>This paper presents a novel approach for accelerating n-body simulations by integrating a physics-informed graph neural networks (GNN) with traditional numerical methods.</li><li>The method uses a leapfrog-based simulation engine to generate datasets from diverse astrophysical scenarios, which are transformed into graph representations.</li><li>A custom-designed GNN is trained to predict particle accelerations with high precision and achieves low prediction errors.</li><li>Experiments demonstrate that the proposed model maintains robust long-term stability and offers a modest speedup of approximately 17% over conventional simulation techniques.</li></ul>

Efficient n-body simulations using physics informed graph neural networks

Discover more