Machine Learning Techniques for Uncertainty Estimation in Dynamic Aperture Prediction

The dynamic aperture is an essential concept in circular particle accelerators, providing the extent of the phase space region where particle motion remains stable over multiple turns. The accurate prediction of the dynamic aperture is key to optimising performance in accelerators such as the CERN L...

Full description

Saved in:
Bibliographic Details
Main Authors: Carlo Emilio Montanari, Robert B. Appleby, Davide Di Croce, Massimo Giovannozzi, Tatiana Pieloni, Stefano Redaelli, Frederik F. Van der Veken
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Computers
Subjects:
Online Access:https://www.mdpi.com/2073-431X/14/7/287
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406560079446016
author Carlo Emilio Montanari
Robert B. Appleby
Davide Di Croce
Massimo Giovannozzi
Tatiana Pieloni
Stefano Redaelli
Frederik F. Van der Veken
author_facet Carlo Emilio Montanari
Robert B. Appleby
Davide Di Croce
Massimo Giovannozzi
Tatiana Pieloni
Stefano Redaelli
Frederik F. Van der Veken
author_sort Carlo Emilio Montanari
collection DOAJ
description The dynamic aperture is an essential concept in circular particle accelerators, providing the extent of the phase space region where particle motion remains stable over multiple turns. The accurate prediction of the dynamic aperture is key to optimising performance in accelerators such as the CERN Large Hadron Collider and is crucial for designing future accelerators like the CERN Future Circular Hadron Collider. Traditional methods for computing the dynamic aperture are computationally demanding and involve extensive numerical simulations with numerous initial phase space conditions. In our recent work, we have devised surrogate models to predict the dynamic aperture boundary both efficiently and accurately. These models have been further refined by incorporating them into a novel active learning framework. This framework enhances performance through continual retraining and intelligent data generation based on informed sampling driven by error estimation. A critical attribute of this framework is the precise estimation of uncertainty in dynamic aperture predictions. In this study, we investigate various machine learning techniques for uncertainty estimation, including Monte Carlo dropout, bootstrap methods, and aleatory uncertainty quantification. We evaluated these approaches to determine the most effective method for reliable uncertainty estimation in dynamic aperture predictions using machine learning techniques.
format Article
id doaj-art-5794d4ca72f4407e9b4cddd50ea1f9ca
institution Kabale University
issn 2073-431X
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Computers
spelling doaj-art-5794d4ca72f4407e9b4cddd50ea1f9ca2025-08-20T03:36:19ZengMDPI AGComputers2073-431X2025-07-0114728710.3390/computers14070287Machine Learning Techniques for Uncertainty Estimation in Dynamic Aperture PredictionCarlo Emilio Montanari0Robert B. Appleby1Davide Di Croce2Massimo Giovannozzi3Tatiana Pieloni4Stefano Redaelli5Frederik F. Van der Veken6Department of Physics and Astronomy, The University of Manchester, Manchester M13 9PL, UKDepartment of Physics and Astronomy, The University of Manchester, Manchester M13 9PL, UKCERN, 1211 Geneva, SwitzerlandCERN, 1211 Geneva, SwitzerlandInstitute of Physics, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, SwitzerlandCERN, 1211 Geneva, SwitzerlandCERN, 1211 Geneva, SwitzerlandThe dynamic aperture is an essential concept in circular particle accelerators, providing the extent of the phase space region where particle motion remains stable over multiple turns. The accurate prediction of the dynamic aperture is key to optimising performance in accelerators such as the CERN Large Hadron Collider and is crucial for designing future accelerators like the CERN Future Circular Hadron Collider. Traditional methods for computing the dynamic aperture are computationally demanding and involve extensive numerical simulations with numerous initial phase space conditions. In our recent work, we have devised surrogate models to predict the dynamic aperture boundary both efficiently and accurately. These models have been further refined by incorporating them into a novel active learning framework. This framework enhances performance through continual retraining and intelligent data generation based on informed sampling driven by error estimation. A critical attribute of this framework is the precise estimation of uncertainty in dynamic aperture predictions. In this study, we investigate various machine learning techniques for uncertainty estimation, including Monte Carlo dropout, bootstrap methods, and aleatory uncertainty quantification. We evaluated these approaches to determine the most effective method for reliable uncertainty estimation in dynamic aperture predictions using machine learning techniques.https://www.mdpi.com/2073-431X/14/7/287surrogate modellinguncertainty quantificationMonte Carlo dropoutbootstrap aggregationdynamic apertureaccelerator modelling
spellingShingle Carlo Emilio Montanari
Robert B. Appleby
Davide Di Croce
Massimo Giovannozzi
Tatiana Pieloni
Stefano Redaelli
Frederik F. Van der Veken
Machine Learning Techniques for Uncertainty Estimation in Dynamic Aperture Prediction
Computers
surrogate modelling
uncertainty quantification
Monte Carlo dropout
bootstrap aggregation
dynamic aperture
accelerator modelling
title Machine Learning Techniques for Uncertainty Estimation in Dynamic Aperture Prediction
title_full Machine Learning Techniques for Uncertainty Estimation in Dynamic Aperture Prediction
title_fullStr Machine Learning Techniques for Uncertainty Estimation in Dynamic Aperture Prediction
title_full_unstemmed Machine Learning Techniques for Uncertainty Estimation in Dynamic Aperture Prediction
title_short Machine Learning Techniques for Uncertainty Estimation in Dynamic Aperture Prediction
title_sort machine learning techniques for uncertainty estimation in dynamic aperture prediction
topic surrogate modelling
uncertainty quantification
Monte Carlo dropout
bootstrap aggregation
dynamic aperture
accelerator modelling
url https://www.mdpi.com/2073-431X/14/7/287
work_keys_str_mv AT carloemiliomontanari machinelearningtechniquesforuncertaintyestimationindynamicapertureprediction
AT robertbappleby machinelearningtechniquesforuncertaintyestimationindynamicapertureprediction
AT davidedicroce machinelearningtechniquesforuncertaintyestimationindynamicapertureprediction
AT massimogiovannozzi machinelearningtechniquesforuncertaintyestimationindynamicapertureprediction
AT tatianapieloni machinelearningtechniquesforuncertaintyestimationindynamicapertureprediction
AT stefanoredaelli machinelearningtechniquesforuncertaintyestimationindynamicapertureprediction
AT frederikfvanderveken machinelearningtechniquesforuncertaintyestimationindynamicapertureprediction