Cosmic Ray Background Removal With Deep Neural Networks in SBND

In liquid argon time projection chambers exposed to neutrino beams and running on or near surface levels, cosmic muons, and other cosmic particles are incident on the detectors while a single neutrino-induced event is being recorded. In practice, this means that data from surface liquid argon time projection chambers will be dominated by cosmic particles, both as a source of event triggers and as the majority of the particle count in true neutrino-triggered events. In this work, we demonstrate a novel application of deep learning techniques to remove these background particles by applying deep learning on full detector images from the SBND detector, the near detector in the Fermilab Short-Baseline Neutrino Program. We use this technique to identify, on a pixel-by-pixel level, whether recorded activity originated from cosmic particles or neutrino interactions.

Download Full-text

Scaling studies for deep learning in Liquid Argon Time Projection Chamber event classification

EPJ Web of Conferences ◽

10.1051/epjconf/201921406016 ◽

2019 ◽

Vol 214 ◽

pp. 06016

Author(s):

Jan Strube ◽

Kolahal Bhattacharya ◽

Eric Church ◽

Jeff Daily ◽

Schram Malachi ◽

...

Keyword(s):

Deep Learning ◽

Time Projection Chamber ◽

Liquid Argon ◽

Classification Problem ◽

Classification Performance ◽

Network Architectures ◽

Neutrino Detectors ◽

Large Size ◽

Learning Techniques ◽

Time Projection

Measurements in Liquid Argon Time Projection Chamber neutrino detectors feature large, high fidelity event images. Deep learning techniques have been extremely successful in classification tasks of photographs, but their application to these event images is challenging, due to the large size of the events, more two orders of magnitude larger than images found in classical challenges like MNIST or ImageNet. This leads to extremely long training cycles, which slow down the exploration of new network architectures and hyperpa-rameter scans to improve the classification performance. We present studies of scaling an LArTPC classification problem on multiple architectures, spanning multiple nodes. The studies are carried out in simulated events in the Micro-BooNE detector.

Download Full-text

First Demonstration of a Pixelated Charge Readout for Single-Phase Liquid Argon Time Projection Chambers

Instruments ◽

10.3390/instruments4010009 ◽

2020 ◽

Vol 4 (1) ◽

pp. 9 ◽

Cited By ~ 2

Author(s):

Jonathan Asaadi ◽

Martin Auger ◽

Antonio Ereditato ◽

Damian Goeldi ◽

Umut Kose ◽

...

Keyword(s):

Single Phase ◽

Signal To Noise Ratio ◽

Liquid Argon ◽

Track Reconstruction ◽

3D Tracking ◽

3D Space ◽

Time Projection Chambers ◽

Event Reconstruction ◽

Phase Liquid ◽

Time Projection

Traditional charge readout technologies of single-phase Liquid Argon Time projection Chambers (LArTPCs) based on projective wire readout introduce intrinsic ambiguities in event reconstruction. Combined with the slow response inherent in LArTPC detectors, reconstruction ambiguities have limited their performance, until now. Here, we present a proof of principle of a pixelated charge readout that enables the full 3D tracking capabilities of LArTPCs. We characterize the signal-to-noise ratio of charge readout chain to be about 14, and demonstrate track reconstruction on 3D space points produced by the pixel readout. This pixelated charge readout makes LArTPCs a viable option for high-multiplicity environments.

Download Full-text

Demonstration of MeV-scale physics in liquid argon time projection chambers using ArgoNeuT

Physical Review D ◽

10.1103/physrevd.99.012002 ◽

2019 ◽

Vol 99 (1) ◽

Cited By ~ 13

Author(s):

R. Acciarri ◽

C. Adams ◽

J. Asaadi ◽

B. Baller ◽

T. Bolton ◽

...

Keyword(s):

Liquid Argon ◽

Time Projection Chambers ◽

Time Projection

Download Full-text

ARAPUCA light trap for large liquid argon time projection chambers

Journal of Physics Conference Series ◽

10.1088/1742-6596/1143/1/012003 ◽

2018 ◽

Vol 1143 ◽

pp. 012003

Author(s):

H da Motta ◽

A A Machado ◽

L Paulucci ◽

E Segreto ◽

A Fauth ◽

...

Keyword(s):

Light Trap ◽

Liquid Argon ◽

Time Projection Chambers ◽

Time Projection

Download Full-text

Benefits of MeV-scale reconstruction capabilities in large liquid argon time projection chambers

Physical Review D ◽

10.1103/physrevd.102.092010 ◽

2020 ◽

Vol 102 (9) ◽

Author(s):

W. Castiglioni ◽

W. Foreman ◽

B. R. Littlejohn ◽

M. Malaker ◽

I. Lepetic ◽

...

Keyword(s):

Liquid Argon ◽

Time Projection Chambers ◽

Time Projection

Download Full-text

Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers

EPJ Web of Conferences ◽

10.1051/epjconf/202125103054 ◽

2021 ◽

Vol 251 ◽

pp. 03054 ◽

Cited By ~ 1

Author(s):

Jeremy Hewes ◽

Adam Aurisano ◽

Giuseppe Cerati ◽

Jim Kowalkowski ◽

Claire Lee ◽

...

Keyword(s):

Neural Network ◽

Message Passing ◽

Liquid Argon ◽

Great Promise ◽

Muon Track ◽

Particle Type ◽

Novel Technique ◽

Time Projection Chambers ◽

Time Projection ◽

The Relationship

This paper presents a graph neural network (GNN) technique for low-level reconstruction of neutrino interactions in a Liquid Argon Time Projection Chamber (LArTPC). GNNs are still a relatively novel technique, and have shown great promise for similar reconstruction tasks in the LHC. In this paper, a multihead attention message passing network is used to classify the relationship between detector hits by labelling graph edges, determining whether hits were produced by the same underlying particle, and if so, the particle type. The trained model is 84% accurate overall, and performs best on the EM shower and muon track classes. The model’s strengths and weaknesses are discussed, and plans for developing this technique further are summarised.

Download Full-text

Felix Based Readout of The Single-Phase Protodune Detector

EPJ Web of Conferences ◽

10.1051/epjconf/201921401013 ◽

2019 ◽

Vol 214 ◽

pp. 01013

Author(s):

Andrea Borga ◽

Eric Church ◽

Frank Filthaut ◽

Enrico Gamberini ◽

Jong Paul de ◽

...

Keyword(s):

Single Phase ◽

Time Windows ◽

Sampling Rate ◽

Liquid Argon ◽

Atlas Collaboration ◽

Short Baseline ◽

Long Baseline ◽

Neutrino Experiments ◽

Time Projection ◽

Anode Plane

The liquid argon Time Projection Chamber technique has matured and is now in use by several short-baseline neutrino experiments. This technology will be used in the long-baseline DUNE experiment; however, this experiment represents a large increase in scale, for which the technology needs to be validated explicitly. To this end, both the single-phase and dual-phase implementations of the technology are being tested at CERN in two full-scale (10 × 10 × 10 m3) ProtoDUNE setups. Besides the detector technology, these setups also allow for extensive tests of readout strategies. The Front-End LInk eXchange (FELIX) system was initially developed within the ATLAS collaboration and is based on custom FPGA-based PCIe I/O cards in combination with commodity servers. FELIX will be used in the single-phase ProtoDUNE setup to read the data coming from 2560 anode wires organized in a single Anode Plane Assembly structure. With a sampling rate of 2 MHz, the system must buffer and process an input rate of 74 Gb/s. Event building requests will arrive at a target rate of 25 Hz, and loss-less compression must reduce the data within the requested time windows before it is sent to the experiment’s event building farm. This paper discusses the design of the system as well as first operational experiences.

Download Full-text

AVOLAR. A high voltage generator for liquid argon time projection chambers

Journal of Instrumentation ◽

10.1088/1748-0221/15/03/c03057 ◽

2020 ◽

Vol 15 (03) ◽

pp. C03057-C03057

Author(s):

L. Romero ◽

J.M. Cela ◽

E. Sanchez Garcia ◽

M. Daniel ◽

M. de Prado

Keyword(s):

High Voltage ◽

Liquid Argon ◽

Time Projection Chambers ◽

Voltage Generator ◽

Time Projection ◽

High Voltage Generator

Download Full-text

NEUTRINOS FROM ICARUS

Acta Polytechnica ◽

10.14311/ap.2013.53.0776 ◽

2013 ◽

Vol 53 (A) ◽

pp. 776-781

Author(s):

Christian Farnese

Keyword(s):

3D Imaging ◽

Sterile Neutrino ◽

Rare Event ◽

Liquid Argon ◽

Good Energy Resolution ◽

Time Projection Chambers ◽

Event Reconstruction ◽

The Status ◽

Good Energy ◽

Time Projection

Liquid Argon Time Projection Chambers are very promising detectors for neutrino and astroparticle physics due to their high granularity, good energy resolution and 3D imaging, allowing for a precise event reconstruction. ICARUS T600 is the largest liquid Argon (LAr) TPC detector ever built (~600 ton LAr mass) and is presently operating underground at the LNGS laboratory. This detector, internationally considered as the milestone towards the realization of the next generation of massive detectors (~tens of ktons) for neutrino and rare event physics, has been smoothly running since summer 2010, collecting data with the CNGS beam and with cosmics. The status of this detector will be shortly described together with the intent to adopt the LAr TPC technology at CERN as a possible solution to the sterile neutrino puzzle.

Download Full-text