English

Toward a Spectral Foundation Model: An Attention-Based Approach with Domain-Inspired Fine-Tuning and Wavelength Parameterization

Instrumentation and Methods for Astrophysics 2023-06-29 v1 Astrophysics of Galaxies Solar and Stellar Astrophysics

Abstract

Astrophysical explorations are underpinned by large-scale stellar spectroscopy surveys, necessitating a paradigm shift in spectral fitting techniques. Our study proposes three enhancements to transcend the limitations of the current spectral emulation models. We implement an attention-based emulator, adept at unveiling long-range information between wavelength pixels. We leverage a domain-specific fine-tuning strategy where the model is pre-trained on spectra with fixed stellar parameters and variable elemental abundances, followed by fine-tuning on the entire domain. Moreover, by treating wavelength as an autonomous model parameter, akin to neural radiance fields, the model can generate spectra on any wavelength grid. In the case with a training set of O(1000), our approach exceeds current leading methods by a factor of 5-10 across all metrics.

Keywords

Cite

@article{arxiv.2306.15703,
  title  = {Toward a Spectral Foundation Model: An Attention-Based Approach with Domain-Inspired Fine-Tuning and Wavelength Parameterization},
  author = {Tomasz Różański and Yuan-Sen Ting and Maja Jabłońska},
  journal= {arXiv preprint arXiv:2306.15703},
  year   = {2023}
}

Comments

7 pages, 3 figures, accepted to ICML 2023 Workshop on Machine Learning for Astrophysics