The first AI simulation of a black hole
High Energy Astrophysical Phenomena
2021-07-01 v1
Abstract
We report the results from our ongoing pilot investigation of the use of deep learning techniques for forecasting the state of turbulent flows onto black holes. Deep neural networks seem to learn well black hole accretion physics and evolve the accretion flow orders of magnitude faster than traditional numerical solvers, while maintaining a reasonable accuracy for a long time.
Keywords
Cite
@article{arxiv.2011.12819,
title = {The first AI simulation of a black hole},
author = {Rodrigo Nemmen and Roberta Duarte and Joao Paulo Navarro},
journal= {arXiv preprint arXiv:2011.12819},
year = {2021}
}
Comments
5 pages, 2 figures. To be published in Proceedings of IAU Symposium No. 359, 2020, "Galaxy evolution and feedback across different environments". Presented in March 2020