Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves. (arXiv:2201.08482v2 [astro-ph.IM] UPDATED)
<a href="http://arxiv.org/find/astro-ph/1/au:+Pimentel_O/0/1/0/all/0/1">Óscar Pimentel</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Estevez_P/0/1/0/all/0/1">Pablo A. Estévez</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Forster_F/0/1/0/all/0/1">Francisco Förster</a>
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-$F_1$score from $approx.525$ to $approx.596$. 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.
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-$F_1$score from $approx.525$ to $approx.596$. 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.
http://arxiv.org/icons/sfx.gif
