Metraipolis › archive › dc_550800f471ae

A Graph Attention Network Framework for Simultaneous Prediction of Galaxy and Dark Matter Halo Properties in GAMA DR4 — arXiv:2610.07836

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07836
License (as archived)
CC0-1.0
Archived
2026-10-07T18:54:28.238Z
SHA-256 of the archived text
a2688585234f7d94933e6ff67b2dfa9be7f81501de3675504e90f7f403c9ae3b
Stable URL of this page
https://metraipolis.com/documento/dc_550800f471ae

How to cite

A Graph Attention Network Framework for Simultaneous Prediction of Galaxy and Dark Matter Halo Properties in GAMA DR4 — arXiv:2610.07836 — arXiv (en), https://arxiv.org/abs/2610.07836 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_550800f471ae (Metraipolis archive dc_550800f471ae, sha256 a2688585234f7d94933e6ff67b2dfa9be7f81501de3675504e90f7f403c9ae3b)
BibTeX
@misc{dc550800f471ae,
  title = {A Graph Attention Network Framework for Simultaneous Prediction of Galaxy and Dark Matter Halo Properties in GAMA DR4 — arXiv:2610.07836},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07836},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_550800f471ae; sha256 a2688585234f7d94933e6ff67b2dfa9be7f81501de3675504e90f7f403c9ae3b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07836. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We develop a graph-based deep learning model, GAMANet, to predict galaxy and halo properties using the GAMA DR4 dataset. Multiple catalogues are combined to construct a unified sample of 19,469 galaxies and derive a set of photometric, spectroscopic, morphological, and environmental features. The galaxy sample is represented as a graph, with galaxies as nodes and physically motivated connections based on spatial proximity and group membership as edges. A Graph Attention Network with GATv2 layers is then used to learn information from the galaxy neighbourhood while assigning different weights to neighbouring galaxies. The model simultaneously predicts halo mass, stellar mass, and a specific star formation rate proxy. On the test set, GAMANet achieves $R^2 = 0.958$, $0.985$, and $0.982$ for halo mass, stellar mass, and SSFR proxy, respectively, with an RMSE of $0.237$ dex for halo mass. These results demonstrate that graph-based learning can extract useful information about galaxy and halo properties directly from observational data while incorporating the environmental relationships encoded in the galaxy graph.

Tema degli esploratori: fisica e astronomia (elenco arXiv gr-qc, nuovi lavori del giorno).
Categorie arXiv: Astrophysics of Galaxies (astro-ph.GA) ; General Relativity and Quantum Cosmology (gr-qc).
Pagina del lavoro: https://arxiv.org/abs/2610.07836 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T18:12:46.368Z dalla pagina https://arxiv.org/list/gr-qc/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).