Multi-Method Machine Learning Classification of Astronomical Sources with Rubin Data Previews: a Spectroscopy-Free Approach with DP1 and DP2
Abstract
We present a multi-method machine-learning study for the binary photometric classification of point-like and extended sources in the Rubin Observatory Data Preview 1 (DP1) and Data Preview 2 (DP2). The workflow runs on the Rubin Science Platform using DP1 and DP2 ugrizy photometry, the DP1 ancillary photometric-redshift catalog, and the Monster astrometric and photometric reference catalog, without relying on external spectroscopy. Six methods (SVM, Random Forest, XGBoost, k-Nearest Neighbors, an Artificial Neural Network, and a soft Voting ensemble) are benchmarked in the deepest DP1 field, the Extended Chandra Deep Field South. These methods reach 10-fold cross-validation macro-F1 scores of 0.95-0.97 on the balanced training subset and test macro-F1 scores of 0.87-0.92 on the imbalanced held-out set, with RF and the SV ensemble tied at the top (0.918); the differences among the leading methods are within the statistical uncertainty. Permutation importance identifies FWHM as the dominant feature, and the six methods agree on 79.5% of the full catalog. The same pipeline is then applied without retuning the settings to the two other DP1 fields with full ugrizy coverage and photometric-redshift support, Euclid Deep Field South and the Low Galactic Latitude Field. Together, the three fields span a factor of approximately 7 in E(B-V) and approximately 10 in stellar density, yet headline macro-F1 remains above 0.87 in every field. We then apply the same pipeline to four DP2 fields (ECDFS, COSMOS, EDFS, and ELAIS-S1). Using colors and morphology, the best method reaches a test macro-F1 of 0.83 to 0.88 across these fields, and the six methods agree on 77 to 86% of each catalog. Adding the per-band photometric uncertainties as features raises the best macro-F1 to about 0.95 in ECDFS DP1 and 0.97 in ECDFS DP2 (and to approximately 0.97-0.98 in the other fields).
Related
- Feature-Based and Deep Learning Methods for Astronomical Light Curve Classification
- Contrastive Astromer: Two-Stage Contrastive Representation Learning for Astronomical Light Curve Classification
- Executable verification through formalized expert reasoning in astronomical spectroscopy
- Machine learning-based classification of type 1 active galactic nuclei
- Data representation matters: Optimising machine learning for X-ray source classification by leveraging spatio-spectral information
BibTeX
@misc{malagon2026multimethod,
title = {{Multi-Method Machine Learning Classification of Astronomical Sources with Rubin Data Previews: a Spectroscopy-Free Approach with DP1 and DP2}},
author = {Andrés Alejandro Plazas Malagón and Yasna Ordenes-Briceño and Dan S. Taranu and Alex Broughton and Yumi Choi and Jeffrey L. Carlin and Sophie Reed and Karla Peña Ramírez and Sean Patrick MacBride and Hurum Maksora Tohfa and Arianna Ranabhat},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.20746},
eprint = {2610.20746},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.20746},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Multi-Method Machine Learning Classification of Astronomical Sources with Rubin Data Previews: a Spectroscopy-Free Approach with DP1 and DP2
AU - Andrés Alejandro Plazas Malagón
AU - Yasna Ordenes-Briceño
AU - Dan S. Taranu
AU - Alex Broughton
AU - Yumi Choi
AU - Jeffrey L. Carlin
AU - Sophie Reed
AU - Karla Peña Ramírez
AU - Sean Patrick MacBride
AU - Hurum Maksora Tohfa
AU - Arianna Ranabhat
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.20746
UR - https://arxiv.org/abs/2610.20746
AB - We present a multi-method machine-learning study for the binary photometric classification of point-like and extended sources in the Rubin Observatory Data Preview 1 (DP1) and Data Preview 2 (DP2). The workflow runs on the Rubin Science Platform using DP1 and DP2 ugrizy photometry, the DP1 ancillary photometric-redshift catalog, and the Monster astrometric and photometric reference catalog, without relying on external spectroscopy. Six methods (SVM, Random Forest, XGBoost, k-Nearest Neighbors, an Artificial Neural Network, and a soft Voting ensemble) are benchmarked in the deepest DP1 field, the Extended Chandra Deep Field South. These methods reach 10-fold cross-validation macro-F1 scores of 0.95-0.97 on the balanced training subset and test macro-F1 scores of 0.87-0.92 on the imbalanced held-out set, with RF and the SV ensemble tied at the top (0.918); the differences among the leading methods are within the statistical uncertainty. Permutation importance identifies FWHM as the dominant feature, and the six methods agree on 79.5% of the full catalog. The same pipeline is then applied without retuning the settings to the two other DP1 fields with full ugrizy coverage and photometric-redshift support, Euclid Deep Field South and the Low Galactic Latitude Field. Together, the three fields span a factor of approximately 7 in E(B-V) and approximately 10 in stellar density, yet headline macro-F1 remains above 0.87 in every field. We then apply the same pipeline to four DP2 fields (ECDFS, COSMOS, EDFS, and ELAIS-S1). Using colors and morphology, the best method reaches a test macro-F1 of 0.83 to 0.88 across these fields, and the six methods agree on 77 to 86% of each catalog. Adding the per-band photometric uncertainties as features raises the best macro-F1 to about 0.95 in ECDFS DP1 and 0.97 in ECDFS DP2 (and to approximately 0.97-0.98 in the other fields).
ER -