Papers
1
Total Citations
5
H-Index
1
About
M. Aubert is a computational astrophysicist whose work sits at the intersection of machine learning and time-domain astronomy. Their primary research focuses on the automated classification and analysis of supernovae, particularly core-collapse supernovae, using deep learning techniques. Aubert’s major contribution is the development of **CCSNscore**, a multi-input deep learning tool designed to classify core-collapse supernovae from spectra obtained by the SED-machine instrument. This work, published in 2025, directly addresses a critical bottleneck in modern astronomy: the overwhelming volume of transient candidates generated by large-scale surveys like the Zwicky Transient Facility (ZTF). By automating the spectral classification process, Aubert’s tool enables rapid identification of supernova subtypes, accelerating the pace of discovery and facilitating follow-up studies. Though a relatively early-career researcher, Aubert’s work has already garnered attention, with the CCSNscore paper accumulating 5 citations in its first year. This contribution is notable for its practical impact, providing the community with a ready-to-use, open-source solution that bridges the gap between big data and physical insight. Aubert represents a new generation of researchers leveraging AI to unlock the secrets of transient phenomena.
Research Focus
Key Achievements
Top Papers
- 1