Using neural networks and clustering algorithms to understand the mass flows and energy cycles at the heart of our Galaxy

Developing machine learning tools to quantify and investigate the global processes that drive star formation in the center of the Milky Way galaxy.
Institution: Liverpool John Moores University

The inner few thousand light years of the Milky Way – the Central Molecular Zone (CMZ) – hosts the nearest supermassive black hole, largest reservoir of dense gas, most massive/dense stellar clusters, and highest volume density of supernovae in the Galaxy. As the nearest environment for which it is possible to simultaneously observe many of the extreme physical processes shaping the Universe, it is one of the most well-studied regions in astrophysics. However, the potential of the CMZ as a laboratory of extreme physics is fundamentally limited by the lack of a unified framework to understand how global processes determine the location, intensity and timescales for star formation and feedback. 

This joint PhD project with the Harvard-Smithsonian Center for Astrophysics will involve working with an international team of researchers to analyse data from the world’s foremost mm-wave telescope, ALMA, intended to overcome this limitation. The project will involve developing both supervised and non-supervised machine learning tools to quantify the range and variation in the physical, kinematic and chemical properties of the gas in the CMZ, and relate these to global processes controlling the mass flows and energy cycles in the centre of the Galaxy.

Throughout the project you will have access to the Astrophysics Research Institute’s postgraduate training programme, as well as to targeted training in data science provided by the Centre for Doctoral Training LIV.INNO. You will also be given the opportunity to carry out a placement at the Harvard-Smithsonian Center for Astrophysics for 12 to 18 months to broaden your wider research and career skills. 

Student: Khang Nguyen

Back to: Centre for Doctoral Training for Innovation in Data Intensive Science