# QuasarNET: Human-level spectral classification and redshifting with Deep Neural Networks

arXiv: https://arxiv.org/abs/1808.09955 · HTML: https://mlsanity.com/paper/1808.09955/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2018.

## Built on by (most cited first, 3 of 3)

- [The information of attribute uncertainties: what convolutional neural networks can learn about errors in input data](https://mlsanity.com/paper/2108.04742/) (2021)
- [Multi-Modal Masked Autoencoders for Learning Image-Spectrum Associations for Galaxy Evolution and Cosmology](https://mlsanity.com/paper/2510.22527/) (2025)
- [Modeling the Central Supermassive Black Holes Mass of Quasars via LSTM Approach](https://mlsanity.com/paper/2301.01459/) (2023)

## Abstract (arXiv)

We introduce QuasarNET, a deep convolutional neural network that performs classification and redshift estimation of astrophysical spectra with human-expert accuracy. We pose these two tasks as a feature detection problem: presence or absence of spectral features determines the class, and their wavelength determines the redshift, very much like human-experts proceed. When ran on BOSS data to identify quasars through their emission lines, QuasarNET defines a sample 99.51±0.03% pure and 99.52±0.03% complete, well above the requirements of many analyses using these data. QuasarNET significantly reduces the problem of line-confusion that induces catastrophic redshift failures to below 0.2%. We also extend QuasarNET to classify spectra with broad absorption line (BAL) features, achieving an accuracy of 98.0±0.4% for recognizing BAL and 97.0±0.2% for rejecting non-BAL quasars. QuasarNET is trained on data of low signal-to-noise and medium resolution, typical of current and future astrophysical surveys, and could be easily applied to classify spectra from current and upcoming surveys such as eBOSS, DESI and 4MOST.