Bayesian Active Learning of Ion Loss-Cone Boundaries in Tokamaks
Abstract
Loss-cone boundary determination in tokamaks is cast as an active learning problem in which a Bayesian logistic regression model with radial basis function features acts as the learner and the guiding-center orbit integrator acts as the labeling method. The approach is applied to an analytic tokamak equilibrium across a mesh of launch positions, producing a database of loss-probability models with approximate posterior uncertainty, each generated within a prescribed trajectory budget. Once generated, the database supports downstream applications, illustrated here with three examples. First, integrating the probability models against a Maxwellian distribution yields the lost-ion fraction and the energy and parallel momentum carried by lost ions, with posterior uncertainty propagated analytically to each integral. Second, a steady balance between the resulting orbit-loss torque and radial angular-momentum diffusion gives co-current edge rotation whose amplitude is set mainly by the prescribed momentum diffusivity and loss-region renewal rate. Third, a neural network surrogate trained on the database learns the in-domain mapping from launch position to loss-probability image, and transport integrals computed from its predictions closely reproduce the Bayesian reference values on held-out samples from the same mesh.
Related
- Shape-Constrained Bayesian Active Learning of Self-Limiting Saturation Curves
- Active matter within flexible boundaries: a novel experimental approach with T. aceti nematodes
- Measurement incompatibility in Bayesian quantum estimation beyond quadratic loss
- Heavy quark energy loss in the Bayesian-inference-improved CUJET model
- Bayesian inference in active microrheology with wall and particle-particle interactions
BibTeX
@misc{lopez2026bayesian,
title = {{Bayesian Active Learning of Ion Loss-Cone Boundaries in Tokamaks}},
author = {Omar E. Lopez and Minglei Yang and Mark Cianciosa and Gary M. Staebler},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36123},
eprint = {2609.36123},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36123},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Bayesian Active Learning of Ion Loss-Cone Boundaries in Tokamaks
AU - Omar E. Lopez
AU - Minglei Yang
AU - Mark Cianciosa
AU - Gary M. Staebler
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.36123
UR - https://arxiv.org/abs/2609.36123
AB - Loss-cone boundary determination in tokamaks is cast as an active learning problem in which a Bayesian logistic regression model with radial basis function features acts as the learner and the guiding-center orbit integrator acts as the labeling method. The approach is applied to an analytic tokamak equilibrium across a mesh of launch positions, producing a database of loss-probability models with approximate posterior uncertainty, each generated within a prescribed trajectory budget. Once generated, the database supports downstream applications, illustrated here with three examples. First, integrating the probability models against a Maxwellian distribution yields the lost-ion fraction and the energy and parallel momentum carried by lost ions, with posterior uncertainty propagated analytically to each integral. Second, a steady balance between the resulting orbit-loss torque and radial angular-momentum diffusion gives co-current edge rotation whose amplitude is set mainly by the prescribed momentum diffusivity and loss-region renewal rate. Third, a neural network surrogate trained on the database learns the in-domain mapping from launch position to loss-probability image, and transport integrals computed from its predictions closely reproduce the Bayesian reference values on held-out samples from the same mesh.
ER -