A Supervised Machine Learning Framework for Multipactor Breakdown Prediction in High-Power Radio Frequency Devices and Accelerator Components: A Case Study in Planar Geometry

2025/07/23 by Asif Iqbal, Iqbal, Asif, John Verboncoeur +3
Engineering · #Accelerator Physics (physics.acc-ph) #Applied Physics (physics.app-ph) #FOS: Computer and information sciences #FOS: Physical sciences #HVDC Systems and Fault Protection #Machine Learning (cs.LG) #Particle accelerators and beam dynamics #Plasma Physics (physics.plasm-ph) #Superconducting Materials and Applications

paper · pdf · doi:10.48550/arxiv.2507.17881

openalex publication_date 2025/07/23 · openalex created_date 2025/10/16 · openalex updated_date 2026/07/28

Abstract

Multipactor is a nonlinear electron avalanche phenomenon that can severely impair the performance of high-power radio frequency (RF) devices and accelerator systems. Accurate prediction of multipactor susceptibility across different materials and operational regimes remains a critical yet computationally intensive challenge in accelerator component design and RF engineering. This study presents the first application of supervised machine learning (ML) for predicting multipactor susceptibility in two-surface planar geometries. A simulation-derived dataset spanning six distinct secondary electron yield (SEY) material profiles is used to train regression models - including Random Forest (RF), Extra Trees (ET), Extreme Gradient Boosting (XGBoost), and funnel-structured Multilayer Perceptrons (MLPs) - to predict the time-averaged electron growth rate, δ_avg. Performance is evaluated using Intersection over Union (IoU), Structural Similarity Index (SSIM), and Pearson correlation coefficient. Tree-based models consistently outperform MLPs in generalizing across disjoint material domains. MLPs trained using a scalarized objective function that combines IoU and SSIM during Bayesian hyperparameter optimization with 5-fold cross-validation outperform those trained with single-objective loss functions. Principal Component Analysis reveals that performance degradation for certain materials stems from disjoint feature-space distributions, underscoring the need for broader dataset coverage. This study demonstrates both the promise and limitations of ML-based multipactor prediction and lays the groundwork for accelerated, data-driven modeling in advanced RF and accelerator system design.

Citations

• Optimal Transport-Based Displacement Interpolation with Data Augmentation for Reduced Order Modeling of Nonlinear Dynamical Systems
• Linac_Gen: integrating machine learning and particle-in-cell methods for enhanced beam dynamics at Fermilab
• Demonstration of Niobium Tin in 218 MHz Low-beta Quarter Wave Accelerator Cavity
• In Search of Lost Domain Generalization
• Invariant Risk Minimization
• Opportunities in Machine Learning for Particle Accelerators
• Multipactor discharge on metals and dielectrics: Historical review and recent theories
• Taking the Human Out of the Loop: A Review of Bayesian Optimization

Related

• Neural Networks as Effective Surrogate Models of Radio-Frequency Quadrupole Particle Accelerator Simulations
• Opportunities in Machine Learning for Particle Accelerators
• Bridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations
• Distance Preserving Machine Learning for Uncertainty Aware Accelerator Capacitance Predictions
• Survey and Benchmarking of Machine Learning Accelerators