SUPR
Studying dark matter with machine learning
Dnr:

NAISS 2023/22-498

Type:

NAISS Small Compute

Principal Investigator:

Harri Waltari

Affiliation:

Uppsala universitet

Start Date:

2023-05-05

End Date:

2023-12-01

Primary Classification:

10301: Subatomic Physics

Webpage:

Allocation

Abstract

This is a project involving me as a supervisor and three undergraduate students working on the project. We are studying how machine learning could help in inferring dark matter properties like its mass and spin from simulated collider data. Computationally the most intensive part is to generate event samples with varying parameters to train the machine learning algorithm and evaluate its performance.