Photometry-only classification of SNe Ia and Ibc reaches >=90% accuracy by fitting a semi-analytical decay model to light curves and using GMMs on the resulting parameter distributions to estimate mixing fractions without any labeled training data.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
astro-ph.IM 2years
2026 2representative citing papers
Attentive Neural Processes outperform Gaussian Processes and neural networks on light curve interpolation quality, feature recovery, calibration, and speed for 15 transient classes under realistic Rubin cadences.
citing papers explorer
-
Photometry is all you need: supernova classification as a mixing problem
Photometry-only classification of SNe Ia and Ibc reaches >=90% accuracy by fitting a semi-analytical decay model to light curves and using GMMs on the resulting parameter distributions to estimate mixing fractions without any labeled training data.
-
Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP
Attentive Neural Processes outperform Gaussian Processes and neural networks on light curve interpolation quality, feature recovery, calibration, and speed for 15 transient classes under realistic Rubin cadences.