Andreas Zoglauer, Staff Researcher

Closed (2) The COSI gamma-ray telescope: Improving the data-analysis pipeline with machine learning

Applications for Fall 2022 are now closed for this project.

COSI, the Compton Spectrometer and Imager, is a NASA-funded gamma-ray telescope which is currently under development and scheduled for launch in 2026. It will observe Galactic nucleosynthesis and positron annihilation, as well as the most violent events in our Universe (supernovae, neutron star mergers) and the most extreme environments (pulsars, black holes).

This project is centered on improving the data analysis pipeline of COSI by applying the latest machine learning tools to individual segments of the pipeline. The available machine learning topics are:
(1) Improve an existing approach for the localization of the gamma-ray interactions in our Germanium detector with a neural network.
(2) Identify background events such as Earth Albedo events, incompletely absorbed events, wrongly reconstructed events, and internal radioactive decays using machine learning on simulated training data sets.
(3) Approximate the imaging response using a deep neural network.
(4) Improve the event reconstruction, i.e., determine the Compton-scatter path of the gamma rays in the detector.

All topics are novel and should - if we get it to work - ultimately lead to published papers.

We will create URAP teams consisting of 3-4 students. Each team will work on one topic and apply the TensorFlow / Keras machine-learning toolkit to it. The ultimate goal is to improve upon the currently existing reference implementations with new, cutting-edge machine learning approaches. The whole team will meet weekly for 1-2 hours with your advisor, but we also expect the URAP team members to meet among themselves regularly to work on the project together. The data sets containing the test and training data will be provided.

The concrete learning goals depend on your chosen topic. In general, they include:
(1) Learn about the data analysis of a modern NASA-funded telescope, COSI
(2) Learn how to use a machine learning toolkit: TensorFlow/Keras
(3) Learn how to apply this toolkit to the data of a modern telescope

Since this is a multi-year project, we prefer students who want to work with us for more than 1 semester. The time spent on the project should be on average at least 6 hours per week, more is strongly preferred.

During the semester, we will predominantly meet and communicate via Zoom, Slack, and email.

Day-to-day supervisor for this project: Dr. Andreas Zoglauer, COSI project scientist.

In your application, please clearly indicated which project(s) you are interested in (COSI, GAPS or both), and let us know how many hours per week you are willing to spend on this research activity.

Qualifications: We will assemble teams of 3-4 students with different experience levels and backgrounds. Thus while the following qualifications apply to seniors, consider these qualifications fully relaxed for first-year students. The desired qualifications are: Interest in Physics and Astrophysics; Data 8 or equivalent; proficiency in Python or C++; prior experience with machine learning (e.g. (deep) neural networks, (random forests of) (boosted) decision trees, support vector machines) and with a common machine learning library recommended (e.g. tensorflow, keras, TMVA); familiarity with the Linux/Unix environment, ssh, bash, and git; great organization and communication skills; punctuality and reliability; talent for multitasking and balancing this project with your normal classes.

Weekly Hours: to be negotiated

Related website: http://cosi.ssl.berkeley.edu
Related website: https://github.com/zoglauer/gamma-ai

Closed (3) Building the GAPS Antarctic Balloon Payload to Probe Dark Matter Using Galactic Particle Signatures

Applications for Fall 2022 are now closed for this project.

The General Antiparticle Spectrometer (GAPS) is a NASA high-altitude balloon mission designed to detect messengers of dark matter interactions in the galaxy. Apprentices are needed to participate in the integration, test, calibration and simulation of the instrument as it prepares for a December 2023 launch from Antarctica.

GAPS is specifically designed to detect antinuclei (antiprotons, antideuterons, and antihelium) in cosmic rays. These particles could be produced through interactions of dark matter in the Galaxy, but they are only rarely produced though other astrophysical processes. Antideuterons in particular are so rare that identification of a single Galactic antideuteron would be evidence of new physics such as dark matter.

The components of the GAPS instrument have been developed by collaborators across the US, Japan, and Italy. This year, we will be assembling the full instrument at Space Sciences Lab in preparation for the inaugural Antarctic balloon flight in late 2023. Apprentices will participate in the integration and testing phase required to transform our novel sensors, readout electronics, and computers into a space-ready detector system.

Depending on your interests and qualifications, you will participate in a subset of the following:
(1) Instrument calibration: Making measurements, characterizing the instrument and analyzing performance with software routines
(2) Instrument simulation: Optimize the capability of the GAPS instrument to identify antiparticles by analyzing simulated data sets.
(3) General payload/instrument integration: Mechanical assembly, making electrical connections, instrument commissioning operations
(4) A robust testing program: Testing electrical systems in thermal/vacuum chambers, qualifying assemblies for flight, developing and executing procedures to properly handle sensitive instrumentation, automating testing/evaluation software
(5) Payload electronics and cabling: With assistance from engineers, small analog, digital, and microcontroller circuits need to be designed, fabricated and tested to control and monitor the payload.
(6) Software: Software to display instrument and payload health and performance is critical to a well-functioning mission, and needs to be designed and deployed.

You will perform these tasks as part of a team consisting of URAP students, scientists, engineers and visiting collaborators. Field Rogers (GAPS postdoc physicist) and engineers at the Space Sciences Laboratory (SSL) will provide day-to-day supervision and mentoring and will work with you to develop an individual project in line with your interests. You will be expected to attend regular meetings with the SSL GAPS team. Much of the work is hands-on and thus requires you to work in-person at the Space Sciences Laboratory. Remote work is possible for software development.

The concrete learning goals depend on your interests. In general, you will:
(1) Develop or deepen fluency with the landscape of interdisciplinary research related to dark matter.
(2) Gain hands-on experience with particle detectors and detector systems and with NASA balloon payloads. You may work with vacuum systems, cryogenic systems, custom analog and digital electronics, operations software and/or analysis software.
(3) Gain instrument calibration and analysis experience.
(4) Improve data visualization and technical communication skills through presentation of your work at local group meetings, GAPS team calls, and/or conferences.

We prefer apprentices who want to work with us for more than 1 semester. We anticipate the opportunity for apprentices to continue research in spring 2023, and possibly a full-time research position in summer 2023. The time spent on the project in the fall semester should be 6 or more hours in a typical week.

In your application, please clearly indicated which project(s) you are interested in (COSI, GAPS or both), and let us know how many hours per week you are willing to spend on this research activity.

Day-to-day supervisor for this project: Field Rogers, Post-Doc

Qualifications: Interest in particle physics, astrophysics, electronics and/or software programming; interest in detectors and high-altitude/space instrumentation; enthusiasm for learning new skills; reliability; organization skills; prior programming or electronics experience helpful but not required.

Weekly Hours: to be negotiated

Off-Campus Research Site: All hands-on work will happen at UC Berkeley's Space Sciences Laboratory (SSL). Please take the free hill shuttle from the Hearst mining circle to the top of the hill. SSL is the last stop (~10 min bus ride).

Related website: https://gaps1.astro.ucla.edu/gaps