Convolutional Neural Network for Extraction of n = 1 Photon Ring of Black Holes

Abstract

Very-long-baseline interferometry (VLBI) may enable direct imaging of fine, event-horizon-scale black hole structures such as the photon ring. In particular, the n = 1 photon subring encodes information about black hole spin in its radial profile and azimuthal brightness modulation, making it a key proxy for spacetime properties. However, the n = 1 subring overlaps with emission from the n = 0 subring in observations, requiring isolation of the n = 1 subring for measurements. We present a convolutional neural network (CNN) capable of extracting the n = 1 subring from composite images containing n = 0 and n = 1 subrings. We simulate 111,000 m -ring images with eht-imaging to train and validate the CNN. The CNN accurately recovers the radial and angular brightness profiles of the n = 1 subring with a mean normalized cross correlation (NXcorr) of ∼0.99. The CNN provides a detection capability by predicting no false positives when input images lack an n = 1 subring. We perform feature extraction with ringfit to show that the CNN-predicted n = 1 subring accurately recovers the ground truth radial profiles and azimuthal brightness modulation, demonstrating the CNN’s capability to extract spin-sensitive features. We further test the CNN on black hole images generated by KerrBAM and general relativistic magnetohydrodynamic (GRMHD) simulations, finding that it recovers the overall n = 1 subring radial profiles while exhibiting discrepancies in the recovered intensity profiles. These results demonstrate the potential of deep learning methods to isolate the n = 1 subring from overlapping emission, providing a framework for analyzing future high-resolution black hole images from proposed VLBI missions such as the Black Hole Explorer (BHEX).

Identification of Magnetic Reconnection in Plasma Turbulence Using a Dual-branch Lightweight Hybrid Convolutional Neural Network
Y. Yin, S. Y. Huang, Q. Y. Xiong +7
The Astrophysical Journal Supplement Series29 Oct 2026Peer-reviewedCC BY 4.0Full textSolar & stellar physicsCrossref
Stacked Hybrid Recurrent Convolutional Neural Network Reconstruction of X-Ray Influence on 21 cm Brightness Temperature
S. Mobina Hosseini, Bahareh S. Salmasi
The Astrophysical Journal30 Sep 2026Peer-reviewedCC BY 4.0Full textSolar & stellar physicsCrossref
Solar Flare Prediction Using a Hybrid Convolutional Neural Network and Transformer Model
Mason Cao, Junwei Zhao
arXiv9 Sep 2026PreprintarXiv licenceFull textInstrumentation & methods Solar & stellar physicsarXiv
Neural Network Guided Parameter Space Constraints for Gravitational Wave Searches from Binary Black Holes
Chetan Verma, Amit Reza, Gurudatt Gaur +2
arXiv23 Sep 2026PreprintarXiv licenceFull textInstrumentation & methods Gravitation & general relativityarXiv
Low-cost neural summaries for cosmological inference: an ensemble of convolutional neural networks trained on approximate simulations
Iñigo Sáez-Casares, Davide Bianchi, Matteo Calabrese +1
arXiv14 Oct 2026PreprintCC BY 4.0Full textCosmologyarXiv

Cite

BibTeX RIS

BibTeX

@article{duong2026convolutional,
  title = {{Convolutional Neural Network for Extraction of n = 1 Photon Ring of Black Holes}},
  author = {Courtney Duong and Frank Myhre and Joseph R. Farah},
  journal = {The Astrophysical Journal},
  year = {2026},
  month = oct,
  doi = {10.3847/1538-4357/aeab91},
  url = {https://iopscience.iop.org/article/10.3847/1538-4357/aeab91},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - Convolutional Neural Network for Extraction of n = 1 Photon Ring of Black Holes
AU  - Courtney Duong
AU  - Frank Myhre
AU  - Joseph R. Farah
PY  - 2026
DA  - 2026/10/27
JO  - The Astrophysical Journal
DO  - 10.3847/1538-4357/aeab91
UR  - https://iopscience.iop.org/article/10.3847/1538-4357/aeab91
AB  - Very-long-baseline interferometry (VLBI) may enable direct imaging of fine, event-horizon-scale black hole structures such as the photon ring. In particular, the n = 1 photon subring encodes information about black hole spin in its radial profile and azimuthal brightness modulation, making it a key proxy for spacetime properties. However, the n = 1 subring overlaps with emission from the n = 0 subring in observations, requiring isolation of the n = 1 subring for measurements. We present a convolutional neural network (CNN) capable of extracting the n = 1 subring from composite images containing n = 0 and n = 1 subrings. We simulate 111,000 m -ring images with eht-imaging to train and validate the CNN. The CNN accurately recovers the radial and angular brightness profiles of the n = 1 subring with a mean normalized cross correlation (NXcorr) of ∼0.99. The CNN provides a detection capability by predicting no false positives when input images lack an n = 1 subring. We perform feature extraction with ringfit to show that the CNN-predicted n = 1 subring accurately recovers the ground truth radial profiles and azimuthal brightness modulation, demonstrating the CNN’s capability to extract spin-sensitive features. We further test the CNN on black hole images generated by KerrBAM and general relativistic magnetohydrodynamic (GRMHD) simulations, finding that it recovers the overall n = 1 subring radial profiles while exhibiting discrepancies in the recovered intensity profiles. These results demonstrate the potential of deep learning methods to isolate the n = 1 subring from overlapping emission, providing a framework for analyzing future high-resolution black hole images from proposed VLBI missions such as the Black Hole Explorer (BHEX).
SN  - 1538-4357
SN  - 0004-637X
ER  -

Abstract

Related

Cite