We present a real-time anomaly detection framework for liquid argon time projection chambers (LArTPCs), targeting applications in particle physics experiments such as the Short Baseline Near Detector or the future Deep Underground Neutrino Experiment. These experiments employ detectors that generate and stream high-resolution but sparse images of neutrino and other particle interactions. Our approach utilizes anomaly detection with autoencoders, compressed through knowledge distillation, to enable the detection of anomalous signals in the data through efficient inference on resource-constrained hardware. The framework is targeted for deployment on computing platforms equipped with field-programmable gate arrays, GPUs, or CPUs, allowing low-latency selection of relevant activity directly from the raw detector data stream. We demonstrate that our approach is suitable for the detection and localization of anomalously "high-multiplicity" activity, and outline promising applications for LArTPC online data filtering and triggering.
@article{arxiv.2509.21817,
title = {Real-time Anomaly Detection for Liquid Argon Time Projection Chambers},
author = {Seokju Chung and Jack Cleeve and Akshay Malige and Georgia Karagiorgi and Lino Gerlach and Adrian A. Pol and Isobel Ojalvo},
journal= {arXiv preprint arXiv:2509.21817},
year = {2026}
}