A review on machine learning for neutrino experiments

  title={A review on machine learning for neutrino experiments},
  author={Fernanda Psihas and Micah Groh and Christopher Tunnell and Karl Warburton},
  journal={arXiv: Computational Physics},
Neutrino experiments study the least understood of the Standard Model particles by observing their direct interactions with matter or searching for ultra-rare signals. The study of neutrinos typically requires overcoming large backgrounds, elusive signals, and small statistics. The introduction of state-of-the-art machine learning tools to solve analysis tasks has made major impacts to these challenges in neutrino experiments across the board. Machine learning algorithms have become an integral… 

Learning Physics from the Machine: An Interpretable Boosted Decision Tree Analysis for the Majorana Demonstrator

This work has presented the first machine learning analysis of the data from the Majorana Demonstrator, and it is claimed that this model is highly compatible with next-generation germanium detector experiments like LEGEND since it can be simultaneously trained on a large number of detectors.

Data Science and Machine Learning in Education

Topics covered include handling, visualizing and adapting structure in data, adapting linear methods to nonlinear problems, density esti-mation, Bayesian statistics, Markov-chain Monte Carlo, variational inference, probabilistic programming,Bayesian model selection, artificial neural networks and deep learning.

Neutrino Characterisation using Convolutional Neural Networks in CHIPS water Cherenkov detectors

This work presents a novel approach to water Cherenkov neutrino detector event reconstruction and classification. Three forms of a Convolutional Neural Network have been trained to reject cosmic muon

A Software Ecosystem for Deploying Deep Learning in Gravitational Wave Physics

  • A. GunnyD. Rankin William Benoit
  • Computer Science
    Proceedings of the 12th Workshop on AI and Scientific Computing at Scale using Flexible Computing Infrastructures
  • 2022
This paper highlights challenges presented by straightforward but naïve deployment strategies for deep learning models, and identifies solutions to them gleaned from these sources, and presents HERMES, a library of tools for implementing these solutions.

Explainable AI for High Energy Physics

Neural Networks are ubiquitous in high energy physics research. However, these highly nonlinear parameterized functions are treated as black boxes - whose inner workings to convey information and

Physics Community Needs, Tools, and Resources for Machine Learning

The needs of the physics community regarding ML across latency and throughput regimes, the tools and resources that can be addressed, and how these can be best utilized and accessed in the coming years are discussed.

Machine learning in the search for new fundamental physics

Georgia Karagiorgi,1, ∗ Gregor Kasieczka,2, † Scott Kravitz,3, ‡ Benjamin Nachman,3, 4, § and David Shih5, ¶ 1Department of Physics, Columbia University, New York, NY 10027, USA 2Institut für

Applications and Techniques for Fast Machine Learning in Science

This community report is intended to give plenty of examples and inspiration for scientific discovery through integrated and accelerated ML solutions, including an abundance of pointers to source material, which can enable these breakthroughs.

Machine Learning Application for Particle Physics: Mexico’s Involvement in the Hyper-Kamiokande Observatory

The present chapter describes the participation of Mexico in theHyper-K observatory, focusing on how ML and supercomputing can be used to design sensors, like the ones found in multi-photomultiplier tube (mPMT) arrays, to be tested on experiments and Hyper-K prototypes.



Neutrino interaction classification with a convolutional neural network in the DUNE far detector

The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure $CP$-violation in the neutrino sector as part of a wider physics program. A deep

Context-enriched identification of particles with a convolutional network for neutrino events

Particle detectors record the interactions of subatomic particles and their passage through matter. The identification of these particles is necessary for in-depth physics analysis. While particles

Neutrino Oscillations and the Solar Neutrino Problem

Part of the interest in neutrino astrophysics has to do with the fascinating interplay between nuclear and particle physics issues — e.g. whether neutrinos are massive and undergo flavor

Volume I. Introduction to DUNE

The preponderance of matter over antimatter in the early universe, the dynamics of the supernovae that produced the heavy elements necessary for life, and whether protons eventually decay—these

The Short Baseline Neutrino Program at Fermilab

The Fermilab Short Baseline Neutrino program has been designed to answer several outstanding questions in the field of neutrino oscillation physics. From the LSND result to the MiniBooNE low energy

DUNE as the Next-Generation Solar Neutrino Experiment.

We show that the Deep Underground Neutrino Experiment (DUNE), with significant but feasible new efforts, has the potential to deliver world-leading results in solar neutrinos. With a 100  kton-yr

Background rejection in NEXT using deep neural networks

We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of

Building for Discovery: Strategic Plan for U.S. Particle Physics in the Global Context

Beginning in 2013, the U.S. particle physics community embarked on a community study to explore our opportunities to move forward into the next era of discovery. The results of this yearlong study

Neutrino oscillations and the solar-neutrino problem.

The values of neutrino masses and mixing angles which are required by the Mikheyev-Smirnov-Wolfenstein (MSW) solution to the solar-neutrino problem are found from analytic solutions to the neutrino

Detecting racial bias in algorithms and machine learning

  • Nicol Turner Lee
  • Business
    Journal of Information, Communication and Ethics in Society
  • 2018
Purpose The online economy has not resolved the issue of racial bias in its applications. While algorithms are procedures that facilitate automated decision-making, or a sequence of unambiguous