Dimensionality Reduction for Studying Diffuse Circumgalactic Medium

Description

The history of a galaxy is encapsulated in the history of its gas cycling between the visible body of the galaxy and its harder-to-detect diffuse circumgalactic medium (CGM). We are researching methods to study the history of the CGM by developing computational and machine learning tools to use quasar absorption lines to determine the gas composition, temperature and density.

The project focuses on applying ML dimensionality reduction techniques for the dataset of simulated quasar absorption spectra.

Duration

Total project length: 175 hours.

Task ideas

Implement machine learning-based dimensionality reduction models applicable to the quasar absorption spectra datasets

Expected results

Reduced dimensional results that will still maintain a high level of accuracy compared to the original dataset

Requirements

Python, previous experience in Machine Learning.

Test

Please use this link to access the test for this project. Tests will be published in March.

Mentors

Jeremy Bailin (University of Alabama)
Jacob Morgan (University of Alabama)
Sergei Gleyzer (University of Alabama)
Jianghao Huyan (University of South Carolina)
Varsha Kulkarni (University of South Carolina)

Please DO NOT contact mentors directly by email. Questions should instead be directed to ml4-sci@cern.ch which is forwarded to mentors. To submit your proposal, CV, and test task solutions, please use this Google form.