Whilst we have some idea about how galaxies evolve, quantifications of their evolutions, particularly in the nearby universe, are still being determined.
With the next generation of telescopes, terabytes of data are being collected each night to help answer this question. In order to examine all of these data, we need fast algorithms to determine the values of age and metallicity of galaxies, which parameterise the evolution of galaxies.
In this talk, I will present my work on creating a machine learning method of analysing large volumes of data efficiently to investigate the evolution history of galaxies. I will show neural networks, which are a type of machine learning, are able to reproduce the properties of galaxies accurately from lower resolution data.