10% off all books and free delivery over £50
Buy from our bookstore and 25% of the cover price will be given to a school of your choice to buy more books. *15% of eBooks.

Domain Generalization With Machine Learning in the NOvA Experiment

View All Editions (1)

The selected edition of this book is not available to buy right now.
Add To Wishlist
Write A Review

About

Domain Generalization With Machine Learning in the NOvA Experiment Synopsis

This thesis presents significant advances in the use of neural networks to study the properties of neutrinos. Machine learning tools like neural networks (NN) can be used to identify the particle types or determine their energies in detectors such as those used in the NOvA neutrino experiment, which studies changes in a beam of neutrinos as it propagates approximately 800 km through the earth. NOvA relies heavily on simulations of the physics processes and the detector response; these simulations work well, but do not match the real experiment perfectly. Thus, neural networks trained on simulated datasets must include systematic uncertainties that account for possible imperfections in the simulation. This thesis presents the first application in HEP of adversarial domain generalization to a regression neural network. Applying domain generalization to problems with large systematic variations will reduce the impact of uncertainties while avoiding the risk offalsely constraining the phase space. Reducing the impact of systematic uncertainties makes NOvA analysis more robust, and improves the significance of experimental results.

About This Edition

ISBN: 9783031435850
Publication date:
Author: Andrew T C Sutton
Publisher: Springer an imprint of Springer Nature Switzerland
Format: Paperback
Pagination: 170 pages
Series: Springer Theses
Genres: Particle and high-energy physics
Machine learning
Scientific standards, measurement etc
Mathematical physics

Frequently asked questions