Deep-TAO: The Deep Learning Transient Astronomical Object data set for Astronomical Transient Event Classification

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Suárez-Pérez, John F., Gómez, Catalina, Neira, Mauricio, Hoyos, Marcela Hernández, Arbeláez, Pablo, Forero-Romero, Jaime E.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910888132345856
author Suárez-Pérez, John F.
Gómez, Catalina
Neira, Mauricio
Hoyos, Marcela Hernández
Arbeláez, Pablo
Forero-Romero, Jaime E.
author_facet Suárez-Pérez, John F.
Gómez, Catalina
Neira, Mauricio
Hoyos, Marcela Hernández
Arbeláez, Pablo
Forero-Romero, Jaime E.
contents We present the Deep-learning Transient Astronomical Object (Deep-TAO), a dataset of 1,249,079 annotated images from the Catalina Real-time Transient Survey, including 3,807 transient and 12,500 non-transient sequences. Deep-TAO has been curated to provide a clean, open-access, and user-friendly resource for benchmarking deep learning models. Deep-TAO covers transient classes such as blazars, active galactic nuclei, cataclysmic variables, supernovae, and events of indeterminate nature. The dataset is publicly available in FITS format, with Python routines and Jupyter notebooks for easy data manipulation. Using Deep-TAO, a baseline Convolutional Neural Network outperformed traditional random forest classifiers trained on light curves, demonstrating its potential for advancing transient classification.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16714
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep-TAO: The Deep Learning Transient Astronomical Object data set for Astronomical Transient Event Classification
Suárez-Pérez, John F.
Gómez, Catalina
Neira, Mauricio
Hoyos, Marcela Hernández
Arbeláez, Pablo
Forero-Romero, Jaime E.
Instrumentation and Methods for Astrophysics
We present the Deep-learning Transient Astronomical Object (Deep-TAO), a dataset of 1,249,079 annotated images from the Catalina Real-time Transient Survey, including 3,807 transient and 12,500 non-transient sequences. Deep-TAO has been curated to provide a clean, open-access, and user-friendly resource for benchmarking deep learning models. Deep-TAO covers transient classes such as blazars, active galactic nuclei, cataclysmic variables, supernovae, and events of indeterminate nature. The dataset is publicly available in FITS format, with Python routines and Jupyter notebooks for easy data manipulation. Using Deep-TAO, a baseline Convolutional Neural Network outperformed traditional random forest classifiers trained on light curves, demonstrating its potential for advancing transient classification.
title Deep-TAO: The Deep Learning Transient Astronomical Object data set for Astronomical Transient Event Classification
topic Instrumentation and Methods for Astrophysics
url https://arxiv.org/abs/2503.16714