Hamiltonian Neural Networks approach to fuzzball geodesics
arXiv:2502.20881 · doi:10.1103/dssv-x49b
Abstract
The recent increase in computational resources and data availability has led to a significant rise in the use of Machine Learning (ML) techniques for data analysis in physics. However, the application of ML methods to solve differential equations capable of describing even complex physical systems is not yet fully widespread in theoretical high-energy physics. Hamiltonian Neural Networks (HNNs) are tools that minimize a loss function defined to solve Hamilton equations of motion. In this work, we implement several HNNs trained to solve, with high accuracy, the Hamilton equations for a massless probe moving inside a smooth and horizonless geometry known as D1-D5 circular fuzzball. We study both planar (equatorial) and non-planar geodesics in different regimes according to the impact parameter, some of which are unstable. Our findings suggest that HNNs could eventually replace standard numerical integrators, as they are equally accurate but more reliable in critical situations.
25 pages + Appendices, 39 figures, minor changes with respect to the previous version
References in corpus (11)
- Adaptable Hamiltonian neural networks
- Solving the Teukolsky equation with physics-informed neural networks
- Turning black-holes and D-branes inside out their photon-spheres
- New Calabi-Yau Manifolds from Genetic Algorithms
- Light rings of five-dimensional geometries
- Using physics-informed neural networks to compute quasinormal modes
- Machine Learned Calabi-Yau Metrics and Curvature
- Unsupervised Machine Learning Techniques for Exploring Tropical Coamoeba, Brane Tilings and Seiberg Duality
- Quasinormal Modes in Modified Gravity using Physics-Informed Neural Networks
- Machine Learning Regularization for the Minimum Volume Formula of Toric Calabi-Yau 3-folds
- Generative AI for Brane Configurations and Coamoeba