LEADER 03910nam 22007095 450 001 9910760294903321 005 20251009094728.0 010 $a3-031-43583-4 024 7 $a10.1007/978-3-031-43583-6 035 $a(MiAaPQ)EBC30876556 035 $a(Au-PeEL)EBL30876556 035 $a(DE-He213)978-3-031-43583-6 035 $a(CKB)28804789100041 035 $a(EXLCZ)9928804789100041 100 $a20231108d2023 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aDomain Generalization with Machine Learning in the NOvA Experiment /$fby Andrew T.C. Sutton 205 $a1st ed. 2023. 210 1$aCham :$cSpringer Nature Switzerland :$cImprint: Springer,$d2023. 215 $a1 online resource (174 pages) 225 1 $aSpringer Theses, Recognizing Outstanding Ph.D. Research,$x2190-5061 311 08$aPrint version: Sutton, Andrew T. C. Domain Generalization with Machine Learning in the NOvA Experiment Cham : Springer International Publishing AG,c2023 9783031435829 327 $aChapter 1: Neutrinos: A Desperate Remedy -- Chapter 2. A Review of Neutrino Physics -- Chapter 3. The NOvA Experiment -- Chapter 4. Event Reconstruction -- Chapter 5. The 3-Flavor Analysis -- Chapter 6. A Long Short-Term Memory Neural Network -- Chapter 7. Domain Generalization by Adversarial Training -- Chapter 8. Conclusion. 330 $aThis thesis presents significant advances in the use of neural networks to study the properties of neutrinos. Machine learning tools like neural networks (NN) can be used to identify the particle types or determine their energies in detectors such as those used in the NOvA neutrino experiment, which studies changes in a beam of neutrinos as it propagates approximately 800 km through the earth. NOvA relies heavily on simulations of the physics processes and the detector response; these simulations work well, but do not match the real experiment perfectly. Thus, neural networks trained on simulated datasets must include systematic uncertainties that account for possible imperfections in the simulation. This thesis presents the first application in HEP of adversarial domain generalization to a regression neural network. Applying domain generalization to problems with large systematic variations will reduce the impact of uncertainties while avoiding the risk of falselyconstraining the phase space. Reducing the impact of systematic uncertainties makes NOvA analysis more robust, and improves the significance of experimental results. 410 0$aSpringer Theses, Recognizing Outstanding Ph.D. Research,$x2190-5061 606 $aParticles (Nuclear physics) 606 $aParticle accelerators 606 $aMeasurement 606 $aMeasuring instruments 606 $aMachine learning 606 $aMathematical physics 606 $aComputer simulation 606 $aParticle Physics 606 $aAccelerator Physics 606 $aMeasurement Science and Instrumentation 606 $aMachine Learning 606 $aComputational Physics and Simulations 615 0$aParticles (Nuclear physics) 615 0$aParticle accelerators. 615 0$aMeasurement. 615 0$aMeasuring instruments. 615 0$aMachine learning. 615 0$aMathematical physics. 615 0$aComputer simulation. 615 14$aParticle Physics. 615 24$aAccelerator Physics. 615 24$aMeasurement Science and Instrumentation. 615 24$aMachine Learning. 615 24$aComputational Physics and Simulations. 676 $a539.72 700 $aSutton$b Andrew T. C$01437616 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910760294903321 996 $aDomain Generalization with Machine Learning in the NOvA Experiment$93598280 997 $aUNINA