Metraipolis › archive › dc_cef1250bfcb0

Feature-Based and Deep Learning Methods for Astronomical Light Curve Classification — arXiv:2611.04664

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04664
License (as archived)
CC0-1.0
Archived
2026-11-04T18:54:10.709Z
SHA-256 of the archived text
5becea69a4eefbc05773dc1c4a2db7543571002d8aafd1a5fa8822e1077e2a89
Stable URL of this page
https://metraipolis.com/documento/dc_cef1250bfcb0

How to cite

Feature-Based and Deep Learning Methods for Astronomical Light Curve Classification — arXiv:2611.04664 — arXiv (en), https://arxiv.org/abs/2611.04664 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cef1250bfcb0 (Metraipolis archive dc_cef1250bfcb0, sha256 5becea69a4eefbc05773dc1c4a2db7543571002d8aafd1a5fa8822e1077e2a89)
BibTeX
@misc{dccef1250bfcb0,
  title = {Feature-Based and Deep Learning Methods for Astronomical Light Curve Classification — arXiv:2611.04664},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04664},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cef1250bfcb0; sha256 5becea69a4eefbc05773dc1c4a2db7543571002d8aafd1a5fa8822e1077e2a89},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04664. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We compare feature-based machine learning and end-to-end deep learning for variable star classification using the Zwicky Transient Facility (ZTF) StarEmbed dataset, which contains about 40,000 objects across seven imbalanced classes. Classical models trained on physically motivated features consistently outperform deep networks trained directly on raw light curves. We find that limited labeled data contributes to the performance gap, while the multivariate, irregularly sampled, and morphologically diverse nature of light curves poses additional challenges for deep learning models. While deep learning holds promise for learning representations directly from observations, our results indicate that current models fail to generalize with the available training set size. These findings motivate further investigation of the benefits of scaling labeled datasets and self-supervised pretraining on large unlabeled surveys. This work establishes a quantitative baseline for future research and highlights the need for further innovations to unlock the potential of deep learning in astronomical time series analysis.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Instrumentation and Methods for Astrophysics (astro-ph.IM).
Pagina del lavoro: https://arxiv.org/abs/2611.04664 — 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 2026-11-04T18:35:37.453Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).