Project Info

Reconstructing ultra-high-energy particle cascades with deep learning methods

Eric Mayotte
emayotte@mines.edu

Project Goals and Description:

In this project the researcher will start to develop a neural network which will reconstruct the mass of an Ultra-High-Energy Cosmic Ray (UHECR) using simulations of the rate at which they deposit energy in the atmosphere. This will require knowledge of python, basic unix usage, and a willingness to struggle with very complex software. As for why this project is interesting: UHECR are single atomic nuclei from other galaxies and are the most energetic phenomena known to humankind. In observing these and using them to increase our astrophysical understanding, two properties are of key importance: the particle's energy and its mass. When one of these particles strikes the top of the atmosphere, they are destroyed and create a high-energy particle cascade which can reach 10 billion particles in size. This project aims to use a new method to maximize the amount of information that can be extracted on the mass of the cosmic ray which if very successful could lead to a revolution on the quality of astrophysics that can be done with current ground-based observatories as well as planned future spaced-based observatories.

More Information:

Grand Challenge: Engineer the tools of scientific discovery.

Primary Contacts:

Eric Mayotte, emayotte@mines.edu

Student Preparation

Qualifications

Required:
  • High proficiency with Python
  • Familiarity with Unix (mac or linux terminal) and SSH
  • Capable of self-directed research
  • To have completed Linear Algebra
  • Familiarity with GitLab and/or GitHub
Advantageous:
  • Familiarity with Python data management packages such as PANDAS
  • Familiarity with KERAS and/or TensorFlow
  • A desire or goal to work with astrophysics, particle physics, or astronomy
  • To have completed Differential Equations

TIME COMMITMENT (HRS/WK)

3-5

SKILLS/TECHNIQUES GAINED

Students will gain:
  • Knowledge of creating and tuning Deep Neural Networks.
  • Skills in big data analysis and visualization
  • Project versioning experience
  • General experience participating in group-based research projects
  • Experience in scientific paper writing for the results of this project.

MENTORING PLAN

  1. An orientation meeting will occur at semester start to bring the student researcher up to speed on the systems, goals, and background needed to complete the project. The expectations, duties, and norms the student will need to meet while carrying out research will also be discussed.
  2. 1-on-1 meetings with the sponsoring faculty will occur once per week to answer student questions, review completed work, and discuss the next steps of the project. Student's career goals and career planning will also be discussed during these meetings.
  3. Twice per semester, once at semester start and once a semester end, a dedicated professional development meeting will take place to ensure that the research project is contributing to the student's long term career goals.
  4. Opportunities to present research both within and outside of Mines will be evaluated and offered depending on rate of project progress.

PREFERRED STUDENT STATUS

Junior
Senior
Return to All Project Page
Share This