English

Full-Spectrum Machine Learning Diagnostics for Interstellar PAHs

Astrophysics of Galaxies 2026-04-22 v2 Instrumentation and Methods for Astrophysics Solar and Stellar Astrophysics

Abstract

In the era of high-sensitivity infrared (IR) astronomy, traditional manual diagnostics are no longer sufficient to harvest the complex physical insights hidden within interstellar spectra. We introduce a machine learning paradigm that bypasses the limitations of empirical band ratios by treating the complete IR spectrum of polycyclic aromatic hydrocarbons (PAHs) as a high-dimensional fingerprint. Using a random forest classifier trained on over 23000 spectra, we achieve a robust F1-score of 0.963 across 12 size and charge categories, maintaining high performance on unseen molecular mixtures. Interrogating the model's decision-making process reveals that PAH size diagnostics are charge-dependent. Neutral PAHs are traced by C-H modes, while ionized species rely on 6-8 micron C-C morphology; however, the 12.5micron feature remains a versatile tracer across multiple charge states. This AI-driven paradigm redefines our understanding of IR signatures, providing a transformative lens to probe the chemical complexity of the interstellar medium.

Keywords

Cite

@article{arxiv.2602.12531,
  title  = {Full-Spectrum Machine Learning Diagnostics for Interstellar PAHs},
  author = {Zhao Wang},
  journal= {arXiv preprint arXiv:2602.12531},
  year   = {2026}
}
R2 v1 2026-07-01T10:34:41.253Z