J-PLUS: Identifying Outlier Spectral Energy Distributions in the Fourth Data Release Using Unsupervised Machine Learning
13 affiliations
- 1Universidade Federal do Espírito Santo
- 2Observatório Nacional
- 3Universidade Federal de Sergipe
- 4NSF NOIRLab
- 5Universidade Federal de Ouro Preto
- 6INAF—Osservatorio Astronomico di Trieste
- 7IFPU—Institute for Fundamental Physics of the Universe
- 8Centro de Astrobiología
- 9Instituto de Astrofísica de Andalucía (IAA-CSIC)
- 10Centro de Estudios de Física del Cosmos de Aragón (CEFCA)
- 11Unidad Asociada CEFCA-IAA
- 12Donostia International Physics Center
- 13Universidade de São Paulo
Abstract
The selection of candidates belonging to rare or underrepresented stellar populations, as well as novel objects, is essential for spectroscopic follow-up. In this work, we demonstrate how combining broadband and narrowband photometric information with machine learning techniques enables this selection. Using photometric data in 12 filters from the Javalambre Photometric Local Universe Survey (J-PLUS) as input, we applied an anomaly detection technique based on autoencoders to identify spectral energy distributions (SEDs) that deviate from the dominant pattern in the sample of J-PLUS objects. Subsequently, we applied the t-distributed stochastic neighbor embedding (t-SNE) algorithm to the J-PLUS colors of the population of outlier SEDs. Combining information from the SIMBAD database and other astronomical surveys to classify the outliers identified by the autoencoder, we are able to characterize overdensities in the t-SNE map. Our study specifically focuses on well-defined islands in the t-SNE space, corresponding to specific populations. We identified a large sample of white dwarfs and low-mass stars, including a small subset of polluted white dwarfs, and report potential candidates for spectroscopic follow-up, including 19 carbon-rich stars, 11 cataclysmic variables, and 170 white dwarf–main-sequence binaries, all previously unreported in the literature.
Versions
Related
- Chromospheric sensitivity of stellar spectral lines: an unsupervised machine learning classification
- Unsupervised selection and characterisation of little red dots in JWST surveys with manifold learning
- X-ray to Mid-IR Spectral Energy Distributions: A Catalog of X-ray Selected AGNs in the XMM-COSMOS Survey
- PHAROS: Panchromatic spectral energy distributions of solar-like stars across evolutionary stages
- Non-thermal emission in jets and winds: Expected emission and spectral index distributions
BibTeX
@article{quispehuaynasi2026jplus,
title = {{J-PLUS: Identifying Outlier Spectral Energy Distributions in the Fourth Data Release Using Unsupervised Machine Learning}},
author = {F. Quispe-Huaynasi and F. Roig and V. Loaiza-Tacuri and V. M. Placco and V. Marra and F. Jiménez-Esteban and A. del Pino and B. Anguiano and J. A. Alzate-Trujillo and S. Daflon and C. López-Sanjuan and P. Cruz and A. Alvarez-Candal and E. Machado-Pereira and J. Alcaniz and R. E. Angulo and J. Cenarro and D. Cristóbal-Hornillos and R. Dupke and A. Ederoclite and A. Hernán-Caballero and C. Hernández-Monteagudo and A. Marin-Franch and M. Moles and L. Sodré and J. Varela and H. Vázquez-Ramió and J. Zaragoza-Cardiel},
journal = {The Astrophysical Journal},
year = {2026},
month = oct,
doi = {10.3847/1538-4357/aeab97},
url = {https://iopscience.iop.org/article/10.3847/1538-4357/aeab97},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - J-PLUS: Identifying Outlier Spectral Energy Distributions in the Fourth Data Release Using Unsupervised Machine Learning
AU - F. Quispe-Huaynasi
AU - F. Roig
AU - V. Loaiza-Tacuri
AU - V. M. Placco
AU - V. Marra
AU - F. Jiménez-Esteban
AU - A. del Pino
AU - B. Anguiano
AU - J. A. Alzate-Trujillo
AU - S. Daflon
AU - C. López-Sanjuan
AU - P. Cruz
AU - A. Alvarez-Candal
AU - E. Machado-Pereira
AU - J. Alcaniz
AU - R. E. Angulo
AU - J. Cenarro
AU - D. Cristóbal-Hornillos
AU - R. Dupke
AU - A. Ederoclite
AU - A. Hernán-Caballero
AU - C. Hernández-Monteagudo
AU - A. Marin-Franch
AU - M. Moles
AU - L. Sodré
AU - J. Varela
AU - H. Vázquez-Ramió
AU - J. Zaragoza-Cardiel
PY - 2026
DA - 2026/10/19
JO - The Astrophysical Journal
DO - 10.3847/1538-4357/aeab97
UR - https://iopscience.iop.org/article/10.3847/1538-4357/aeab97
AB - The selection of candidates belonging to rare or underrepresented stellar populations, as well as novel objects, is essential for spectroscopic follow-up. In this work, we demonstrate how combining broadband and narrowband photometric information with machine learning techniques enables this selection. Using photometric data in 12 filters from the Javalambre Photometric Local Universe Survey (J-PLUS) as input, we applied an anomaly detection technique based on autoencoders to identify spectral energy distributions (SEDs) that deviate from the dominant pattern in the sample of J-PLUS objects. Subsequently, we applied the t-distributed stochastic neighbor embedding (t-SNE) algorithm to the J-PLUS colors of the population of outlier SEDs. Combining information from the SIMBAD database and other astronomical surveys to classify the outliers identified by the autoencoder, we are able to characterize overdensities in the t-SNE map. Our study specifically focuses on well-defined islands in the t-SNE space, corresponding to specific populations. We identified a large sample of white dwarfs and low-mass stars, including a small subset of polluted white dwarfs, and report potential candidates for spectroscopic follow-up, including 19 carbon-rich stars, 11 cataclysmic variables, and 170 white dwarf–main-sequence binaries, all previously unreported in the literature.
SN - 0004-637X
SN - 1538-4357
ER -