# Classifying Image Sequences of Astronomical Transients with Deep Neural Networks

arXiv: https://arxiv.org/abs/2004.13877 · HTML: https://mlsanity.com/paper/2004.13877/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 6 of 6)

- [A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients](https://mlsanity.com/paper/2103.12102/) (2021)
- [Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers](https://mlsanity.com/paper/2405.03730/) (2024)
- [Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves](https://mlsanity.com/paper/2201.08482/) (2022)
- [PNet -- A Deep Learning Based Photometry and Astrometry Bayesian Framework](https://mlsanity.com/paper/2106.14349/) (2021)
- [Identifying Transients in the Dark Energy Survey using Convolutional Neural Networks](https://mlsanity.com/paper/2203.09908/) (2022)
- [Image-Based Multi-Survey Classification of Light Curves with a Pre-Trained Vision Transformer](https://mlsanity.com/paper/2507.11711/) (2025)

## Abstract (arXiv)

Supervised classification of temporal sequences of astronomical images into meaningful transient astrophysical phenomena has been considered a hard problem because it requires the intervention of human experts. The classifier uses the expert's knowledge to find heuristic features to process the images, for instance, by performing image subtraction or by extracting sparse information such as flux time series, also known as light curves. We present a successful deep learning approach that learns directly from imaging data. Our method models explicitly the spatio-temporal patterns with Deep Convolutional Neural Networks and Gated Recurrent Units. We train these deep neural networks using 1.3 million real astronomical images from the Catalina Real-Time Transient Survey to classify the sequences into five different types of astronomical transient classes. The TAO-Net (for Transient Astronomical Objects Network) architecture outperforms the results from random forest classification on light curves by 10 percentage points as measured by the F1 score for each class; the average F1 over classes goes from 45% with random forest classification to 55% with TAO-Net. This achievement with TAO-Net opens the possibility to develop new deep learning architectures for early transient detection. We make available the training dataset and trained models of TAO-Net to allow for future extensions of this work.