The first AI simulation of a black hole

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 traditio...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the International Astronomical Union 2020-03, Vol.15 (S359), p.329-333
Main Authors: Nemmen, Rodrigo, Duarte, Roberta, Navarro, João P.
Format: Article
Language:English
Subjects:
Artificial neural networks
Astronomy
Black holes
Computational fluid dynamics
Contributed Papers
Deposition
Machine learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1743-9213
1743-9221
DOI:10.1017/S1743921320003981