This study focuses on two different types of learning that can be derived from as-tronomy: machine learning to examine galaxies and inform their evolution, andusing astronomy as an inspiring vehicle to develop skills useful to underrepresentedaudiences.Upcoming large-area narrow-band photometric surveys will observe a largenumber of galaxies efficiently. However, it will be computationally challenging toanalyse the stellar populations of galaxies from such big data to investigate theirformation and evolutionary histories. We have applied a convolutional neural net-work (CNN) technique to retrieve the metallicity and age from narrow-band dataefficiently. The CNN was trained using synthetic photometry from the integral fieldunit spectra and the age and metallicity obtained from spectral analysis. We showthat our CNN model can recover age and metallicity from narrow-band data. Wealso find that the diversity of the dataset for training the CNN has a significant im-pact on the accuracy of its predictions. Hence, future applications of CNNs requirehigh quality spectroscopic data from a diverse population of galaxies.This study also presents a way to use astronomy to engage with the novel au-dience of jobseekers to co-create a mutually beneficial method of engagement. Weworked with people looking for work in the cultural sector. We ran an online sur-vey to assess participants’ interest in science and what career-relevant skills theydesired. We found that many of the skills which our participants are interested inare aligned with skills needed for astronomy research. Though our participants feltdisconnected from science they still maintained an interest in learning about astron-omy. We also ran a co-creation session to collaboratively create a skills-focused
astronomy pilot workshop. We find three themes arising from the co-creation ses-sion, which have implications for effective engagement with audiences who feeldisconnected from science.