Neural Network identification of Dark Star Candidates. II. Spectroscopy

TL;DR

This paper develops a neural network model trained on synthetic spectra to rapidly identify spectroscopic Dark Star candidates in JWST data, confirming some previously identified candidates and enabling faster analysis of high-redshift objects.

Contribution

A new neural network approach for spectroscopic identification of Dark Stars that is over 10,000 times faster than traditional methods.

Findings

Validated neural network on real JWST data confirming Dark Star candidates.

Achieved parameter predictions in milliseconds, vastly outperforming previous methods.

Established a robust tool for future high-redshift Dark Star studies.

Abstract

Some of the first stars in the Universe might be powered by Dark Matter (DM) annihilations, rather than nuclear fusion. Those objects, i.e. Dark stars (DS), offer a unique window into understanding DM via the observational study of the formation and evolution of the first stars and their Black Hole (BH) remnants. In \cite{NNSMDSPhot} (Paper~I) we introduced a feedforward neural network (FFNN) trained on synthetic DS photometry in order to detect and characterize dark star {\it photometric} candidates in the early universe based on data taken with the NIRCam instrument onboard the James Webb Space Telescope (JWST). In this work we develop a FFNN trained on synthetic DS spectra in order to identify {\it spectroscopic} dark star candidates in the data taken with JWST's NIRSpec instrument. In order to validate our FFNN model we apply it to real data for the four spectroscopic Supermassive Dark Star (SMDS) candidates recently identified in \cite{ilie2025spectroscopicsupermassivedarkstar} and reconfirm that indeed \JADESeleven, \JADESzthirteen, \JADESfz, and \JADESfo have spectra that are consistent with those of Supermassive Dark Stars. The main advantage of our FFNN model, in comparison to the Nedleaer-Mead Monte Carlo parameter estimator used in \cite{ilie2025spectroscopicsupermassivedarkstar}, is that the approach introduced here predicts parameters in milliseconds, over 10,000 times faster than the traditional method used in \cite{ilie2025spectroscopicsupermassivedarkstar}. With this in mind, the FFNN model we developed and validated in this work will be adapted for Bayesian uncertainty analyses and automatic analyses of NIRSpec publicly available data for high redshift objects. This study establishes a robust and efficient tool for probing Dark Stars and understanding their role in cosmic evolution.