Liew-Cain, Choong Ling;
(2023)
Learning with Astronomy:
Neural Network Studies of Galaxy
Evolution and Inspiring, Skill Based
Learning.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Liew-Cain_10168236_thesis_sig_removed.pdf Download (23MB) | Preview |
Abstract
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.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Learning with Astronomy: Neural Network Studies of Galaxy Evolution and Inspiring, Skill Based Learning |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2023. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Space and Climate Physics |
| URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10168236 |
Archive Staff Only
 |
View Item |
