Unsupervise Machine Learning on Astrochemical Spectra
A study on high-mass star-forming regions
J. Alonso Garcia (TU Delft - Aerospace Engineering)
K.J. Cowan – Graduation committee member (TU Delft - Astrodynamics & Space Missions)
W. van der Wal – Graduation committee member (TU Delft - Planetary Exploration)
A. Sánchez-Monge – Mentor (ICE-CSIC)
S.M. Cazaux – Mentor (TU Delft - Planetary Exploration)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
High-mass stars are one of the main drivers that shape the galaxy. Understanding the process through which they form is therefore of the utmost importance. This process, however, is not yet fully understood. Contributing to this field, the ALMAGAL survey has studied over 6000 star-forming regions with a higher resolution than any other survey before. On one hand, this data will help scientists study these obscure regions and draw a clearer picture of the high-mass star-formation process. On the other hand, the sheer volume and complexity of the data produced by this survey is far too great for conventional methods to handle swiftly.
This thesis therefore explores the use of unsupervised machine learning (ML) methods to cluster astrochemical spectra from the ALMAGAL survey. The aim of this thesis is to explore which models are best suited for the task, and to use the resulting clusters to establish a chemical evolutionary sequence for high-mass star-forming regions.....
https://github.com/ javialonso05/MSc-Thesis