Authors:

Siddhant Jain

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

Gamma-ray spectroscopy is used by nuclear physicists to better understand the structure of the nucleus in excited states. By observing the decays from an excited nucleus, we can deduce its allowed energy states and transitions that might reveal promising applications for specific states called "isomers". Isomers are states with a comparably long life- time, allowing for the storage of energy. However, few suitable isomer states are currently known, and more sensitive analysis techniques and more data in general are required to identify more isomer states. The current analysis techniques demands human-based expert labor, making isomer identification slow and prone to bias and omissions. We develop a machine learning (ML) analysis technique by recasting the task as an image-to-graph translation problem. We explore different solutions for this problem and build intuition by using a custom Monte-Carlo-derived toy data set for training and validation prior to analyzing actual data with small signal yield of < 1%. Our aim is to deliver an analysis framework capable of carrying out spectroscopy substantially faster, with minimized bias, and reproducible. Keywords: Gamma Ray Spectroscopy; Machine Learning; Nuclear Physics; Monte Carlo; Level Scheme

Source:

Purdue University / 2025

Topics:

No topics listed

Co-authors:

Siddhant Jain