# Predicting galaxy spectra from images with hybrid convolutional neural networks

arXiv: https://arxiv.org/abs/2009.12318 · HTML: https://mlsanity.com/paper/2009.12318/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 4 of 4)

- [The Platonic Universe: Do Foundation Models See the Same Sky?](https://mlsanity.com/paper/2509.19453/) (2025)
- [Elements of effective machine learning datasets in astronomy](https://mlsanity.com/paper/2211.14401/) (2022)
- [AstroCLIP: A Cross-Modal Foundation Model for Galaxies](https://mlsanity.com/paper/2310.03024/) (2023)
- [Integral Field Unit Spectroscopy with One Fiber](https://mlsanity.com/paper/2606.10197/) (2026)

## Abstract (arXiv)

Galaxies can be described by features of their optical spectra such as oxygen emission lines, or morphological features such as spiral arms. Although spectroscopy provides a rich description of the physical processes that govern galaxy evolution, spectroscopic data are observationally expensive to obtain. For the first time, we are able to robustly predict galaxy spectra directly from broad-band imaging. We present a powerful new approach using a hybrid convolutional neural network with deconvolution instead of batch normalization; this hybrid CNN outperforms other models in our tests. The learned mapping between galaxy imaging and spectra will be transformative for future wide-field surveys, such as with the Vera C. Rubin Observatory and Nancy Grace Roman Space Telescope, by multiplying the scientific returns for spectroscopically-limited galaxy samples.