# Advancing accelerator virtual beam diagnostics through latent evolution modeling: an integrated solution to forward, inverse, tuning, and UQ problems

arXiv: https://arxiv.org/abs/2602.22618 · HTML: https://mlsanity.com/paper/2602.22618/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 37 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 10 of 10)

- [Superconducting radio-frequency cavity fault classification using machine learning at Jefferson Laboratory](https://mlsanity.com/paper/2006.06562/) (2020)
- [A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators](https://mlsanity.com/paper/2403.13858/) (2024)
- [Physics-Based Deep Neural Networks for Beam Dynamics in Charged Particle Accelerators](https://mlsanity.com/paper/2007.03555/) (2020)
- [High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networks](https://mlsanity.com/paper/2101.10437/) (2021)
- [Tuning Particle Accelerators with Safety Constraints using Bayesian Optimization](https://mlsanity.com/paper/2203.13968/) (2022)
- [Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal](https://mlsanity.com/paper/2408.07847/) (2024)
- [Robust Errant Beam Prognostics with Conditional Modeling for Particle Accelerators](https://mlsanity.com/paper/2312.10040/) (2023)
- [Online Multi-Objective Particle Accelerator Optimization of the AWAKE Electron Beam Line for Simultaneous Emittance and Orbit Control](https://mlsanity.com/paper/2003.11155/) (2020)
- [Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities](https://mlsanity.com/paper/2202.05610/) (2022)
- [Classifier-pruned Bayesian optimization for particle accelerator tuning: Exploring temporally structured manifold of 6D beam phase space](https://mlsanity.com/paper/2412.01748/) (2024)

## Abstract (arXiv)

Virtual beam diagnostics relies on computationally intensive beam dynamics simulations where high-dimensional charged particle beams evolve through the accelerator. We propose Latent Evolution Model (LEM), a hybrid machine learning framework with an autoencoder that projects high-dimensional phase spaces into lower-dimensional representations, coupled with transformers to learn temporal dynamics in the latent space. This approach provides a common foundational framework addressing multiple interconnected challenges in beam diagnostics. For textitforward modeling, a Conditional Variational Autoencoder (CVAE) encodes 15 unique projections of the 6D phase space into a latent representation, while a transformer predicts downstream latent states from upstream inputs. For textitinverse problems, we address two distinct challenges: (a) predicting upstream phase spaces from downstream observations by utilizing the same CVAE architecture with transformers trained on reversed temporal sequences along with aleatoric uncertainty quantification, and (b) estimating RF settings from the latent space of the trained LEM using a dedicated dense neural network that maps latent representations to RF parameters. For textittuning problems, we leverage the trained LEM and RF estimator within a Bayesian optimization framework to determine optimal RF settings that minimize beam loss. This paper summarizes our recent efforts and demonstrates how this unified approach effectively addresses these traditionally separate challenges.