Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves

by   Óscar Pimentel, et al.

In astronomical surveys, such as the Zwicky Transient Facility (ZTF), supernovae (SNe) are relatively uncommon objects compared to other classes of variable events. Along with this scarcity, the processing of multi-band light-curves is a challenging task due to the highly irregular cadence, long time gaps, missing-values, low number of observations, etc. These issues are particularly detrimental for the analysis of transient events with SN-like light-curves. In this work, we offer three main contributions. First, based on temporal modulation and attention mechanisms, we propose a Deep Attention model called TimeModAttn to classify multi-band light-curves of different SN types, avoiding photometric or hand-crafted feature computations, missing-values assumptions, and explicit imputation and interpolation methods. Second, we propose a model for the synthetic generation of SN multi-band light-curves based on the Supernova Parametric Model (SPM). This allows us to increase the number of samples and the diversity of the cadence. The TimeModAttn model is first pre-trained using synthetic light-curves in a semi-supervised learning scheme. Then, a fine-tuning process is performed for domain adaptation. The proposed TimeModAttn model outperformed a Random Forest classifier, increasing the balanced-F_1score from ≈.525 to ≈.596. The TimeModAttn model also outperformed other Deep Learning models, based on Recurrent Neural Networks (RNNs), in two scenarios: late-classification and early-classification. Finally, we conduct interpretability experiments. High attention scores are obtained for observations earlier than and close to the SN brightness peaks, which are supported by an early and highly expressive learned temporal modulation.


Classifying Image Sequences of Astronomical Transients with Deep Neural Networks

Supervised classification of temporal sequences of astronomical images i...

Near-infrared Mira Period-Luminosity Relations in M33

We analyze sparsely-sampled near-infrared (JHKs) light curves of a sampl...

Real-time detection of anomalies in large-scale transient surveys

New time-domain surveys, such as the Rubin Observatory Legacy Survey of ...

RAPID: Early Classification of Explosive Transients using Deep Learning

We present RAPID (Real-time Automated Photometric IDentification), a nov...

Modeling Stochastic Variability in Multi-Band Time Series Data

In preparation for the era of the time-domain astronomy with upcoming la...

Scalable End-to-end Recurrent Neural Network for Variable star classification

During the last decade, considerable effort has been made to perform aut...

Supernova Light Curves Approximation based on Neural Network Models

Photometric data-driven classification of supernovae becomes a challenge...

Please sign up or login with your details

Forgot password? Click here to reset