Self-learning neural network cracks iconic black holes
Using supercomputers and software at the MPCDF, a team of astronomers led by Michael Janssen (Radboud University, The Netherlands and MPI for Radioastronomy, Bonn) has trained a neural network with millions of synthetic black hole data sets.
A team of astronomers led by Michael Janssen (Radboud University, The Netherlands and MPI for Radioastronomy, Bonn) has trained a neural network with millions of synthetic black hole data sets. Based on the network and data from the Event Horizon Telescope, they now predict, among other things, that the black hole at the center of our Milky Way is spinning at near top speed. The astronomers publish their results and methodology in three papers in the journal Astronomy & Astrophysics.
"The ability to scale up to millions of synthetic data files is an impressive achievement that significantly enhanced our capacity for black hole testing." says co-researcher Jordy Davelaar (Princeton University, USA). "You need storage capacity, a supercomputer, a software pipeline, and a program that distributes the work." The researchers stress that this scale of work was made possible by a coordinated ecosystem of computational services which includes MPCDF supercomputers for the neural network training, and using software tools including TensorFlow, Horovod, and CASA.
References and further reading:
- Original press release
- Deep learning inference with the Event Horizon Telescope I. Calibration improvements and a
comprehensive synthetic data library. By: M. Janssen et al. In: Astronomy & Astrophysics, 6
June 2025 - Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for
Bayesian artificial neural networks. By: M. Janssen et al. In: Astronomy & Astrophysics, 6
June 2025 - Deep learning inference with the Event Horizon Telescope III. Zingularity results from the
2017 observations and predictions for future array expansions. By: M. Janssen et al. In:
Astronomy & Astrophysics, 6 June 2025