Evaluating machine learning models for supernova gravitational wave signal classification

Y. Sultan Abylkairov, Matthew C Edwards, Daniil Orel, Ayan Mitra, Bekdaulet Shukirgaliyev, Ernazar B. Abdikamalov

Machine Learning Science and Technology 2024 article cited by 7

Source Open-access PDF More in Physics & Astronomy

importance 4/10 ai assisted Pulsars and Gravitational Waves Research astrophysics stage: research

Problem

Determining the equation of state of nuclear matter from gravitational waves of rotating core-collapse supernovae requires classifying signals generated by different equations of state.

Why it matters

The nuclear equation of state is fundamental to understanding supernovae and dense matter.

What the AI did

Trained convolutional and recurrent neural networks plus six classical algorithms to classify simulated GW signals by equation of state, and tested GREP-approximated signals.

Results

All models except naïve Bayes achieved over 90% accuracy; models trained on GREP data showed low accuracy.

Impact

Shows ML can classify simulated supernova GW signals by EOS, but GREP approximation degrades accuracy.

Record

Venue	Machine Learning Science and Technology
Published	2024
Work type	article
Authors	Y. Sultan Abylkairov, Matthew C Edwards, Daniil Orel, Ayan Mitra, Bekdaulet Shukirgaliyev, Ernazar B. Abdikamalov
Citations	7 (OpenAlex, at import time)
References	99
Model or method	CNN, RNN, random forest, SVM, naïve Bayes, logistic regression, k-NN, XGBoost
Organization	not stated in source
Primary source	https://doi.org/10.1088/2632-2153/ada33a
Open access	gold
Keywords	gravitational waves, core-collapse supernovae, machine learning, equation of state, classification

Importance rating

4 / 10

real but narrower advance

Probing the nuclear equation of state via supernova GW signals is fundamental science, but the work is simulation-based classification with noted limitations; no scale stated.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Physics & Astronomy

#	Paper	Year	Citations	Importance
1	Magnetic control of tokamak plasmas through deep reinforcement learning Jonas Degrave, Federico Felici, Jonas Buchli, Michael Neunert, Brendan...	2022	739	7
2	Solving the quantum many-body problem with artificial neural networks Giuseppe Carleo, Matthias Troyer	2017	2,205	7
3	Learning high-accuracy error decoding for quantum processors Johannes Bausch, Andrew Senior, Francisco J. H. Heras, Thomas Edlich,...	2024	90	7
4	Optimizing Quantum Error Correction Codes with Reinforcement Learning Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Brie...	2019	158	7
5	Machine-learning-assisted correction of correlated qubit errors in a topological code Paul Baireuther, Thomas E. O’Brien, Brian Tarasinski, C. W. J. Beenakk...	2018	141	7