Saved in:
Bibliographic Details
Main Authors: Wheeler, Tyler, Kuchera, Michelle P., Ramanujan, Raghuram, Krupp, Ryan, Wrede, Chris, Ravishankar, Saiprasad, Cross, Connor L., Heung, Hoi Yan Ian, Jones, Andrew J., Votaw, Benjamin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.11221
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911265908064256
author Wheeler, Tyler
Kuchera, Michelle P.
Ramanujan, Raghuram
Krupp, Ryan
Wrede, Chris
Ravishankar, Saiprasad
Cross, Connor L.
Heung, Hoi Yan Ian
Jones, Andrew J.
Votaw, Benjamin
author_facet Wheeler, Tyler
Kuchera, Michelle P.
Ramanujan, Raghuram
Krupp, Ryan
Wrede, Chris
Ravishankar, Saiprasad
Cross, Connor L.
Heung, Hoi Yan Ian
Jones, Andrew J.
Votaw, Benjamin
contents Time Projection Chambers (TPCs) are versatile detectors that reconstruct charged-particle tracks in an ionizing medium, enabling sensitive measurements across a wide range of nuclear physics experiments. We explore sparse convolutional networks for representation learning on TPC data, finding that a sparse ResNet architecture, even with randomly set weights, provides useful structured vector embeddings of events. Pre-training this architecture on a simple physics-motivated binary classification task further improves the embedding quality. Using data from the GAseous Detector with GErmanium Tagging (GADGET) II TPC, a detector optimized for measuring low-energy $β$-delayed particle decays, we represent raw pad-level signals as sparse tensors, train Minkowski Engine ResNet models, and probe the resulting event-level embeddings which reveal rich event structure. As a cross-detector test, we embed data from the Active-Target TPC (AT-TPC) -- a detector designed for nuclear reaction studies in inverse kinematics -- using the same encoder. We find that even an untrained sparse ResNet model provides useful embeddings of AT-TPC data, and we observe improvements when the model is trained on GADGET data. Together, these results highlight the potential of sparse convolutional techniques as a general tool for representation learning in diverse TPC experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11221
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sparse Methods for Vector Embeddings of TPC Data
Wheeler, Tyler
Kuchera, Michelle P.
Ramanujan, Raghuram
Krupp, Ryan
Wrede, Chris
Ravishankar, Saiprasad
Cross, Connor L.
Heung, Hoi Yan Ian
Jones, Andrew J.
Votaw, Benjamin
Machine Learning
Nuclear Experiment
Time Projection Chambers (TPCs) are versatile detectors that reconstruct charged-particle tracks in an ionizing medium, enabling sensitive measurements across a wide range of nuclear physics experiments. We explore sparse convolutional networks for representation learning on TPC data, finding that a sparse ResNet architecture, even with randomly set weights, provides useful structured vector embeddings of events. Pre-training this architecture on a simple physics-motivated binary classification task further improves the embedding quality. Using data from the GAseous Detector with GErmanium Tagging (GADGET) II TPC, a detector optimized for measuring low-energy $β$-delayed particle decays, we represent raw pad-level signals as sparse tensors, train Minkowski Engine ResNet models, and probe the resulting event-level embeddings which reveal rich event structure. As a cross-detector test, we embed data from the Active-Target TPC (AT-TPC) -- a detector designed for nuclear reaction studies in inverse kinematics -- using the same encoder. We find that even an untrained sparse ResNet model provides useful embeddings of AT-TPC data, and we observe improvements when the model is trained on GADGET data. Together, these results highlight the potential of sparse convolutional techniques as a general tool for representation learning in diverse TPC experiments.
title Sparse Methods for Vector Embeddings of TPC Data
topic Machine Learning
Nuclear Experiment
url https://arxiv.org/abs/2511.11221