University of Sussex
Browse
- No file added yet -

Learning the relationship between galaxies spectra and their star formation histories using convolutional neural etworks and cosmological simulations

Download (5.31 MB)
Version 2 2023-06-12, 09:12
Version 1 2023-06-09, 19:21
journal contribution
posted on 2023-06-12, 09:12 authored by Christopher Lovell, Viviana Acquaviva, Peter Thomas, Kartheik G Iyer, Eric Gawiser, Stephen WilkinsStephen Wilkins
We present a new method for inferring galaxy star formation histories (SFH) using machine learning methods coupled with two cosmological hydrodynamic simulations. We train Convolutional Neural Networks to learn the relationship between synthetic galaxy spectra and high resolution SFHs from the EAGLE and Illustris models. To evaluate our SFH reconstruction we use Symmetric Mean Absolute Percentage Error (SMAPE), which acts as a true percentage error in the low-error regime. On dust-attenuated spectra we achieve high test accuracy (median SMAPE = 10.5%). Including the effects of simulated observational noise increases the error (12.5%), however this is alleviated by including multiple realisations of the noise, which increases the training set size and reduces overfitting (10.9%). We also make estimates for the observational and modelling errors. To further evaluate the generalisation properties we apply models trained on one simulation to spectra from the other, which leads to only a small increase in the error (median SMAPE ~15%?). We apply each trained model to SDSS DR7 spectra, and find smoother histories than in the VESPA catalogue. This new approach complements the results of existing SED fitting techniques, providing star formation histories directly motivated by the results of the latest cosmological simulations.

History

Publication status

  • Published

File Version

  • Accepted version

Journal

Monthly Notices Of The Royal Astronomical Society

ISSN

0035-8711,

Publisher

Oxford University Press

Department affiliated with

  • Physics and Astronomy Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2019-10-14

First Open Access (FOA) Date

2019-10-14

First Compliant Deposit (FCD) Date

2019-10-14

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC