mlsanityData to 7 Oct 2026

A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators

arXiv 2403.13858 ↗First posted 19 Mar 2024physics.acc-ph cs.CV cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Particle accelerators are complex systems that focus, guide, and accelerate intense charged particle beams to high energy. Beam diagnostics present a challenging problem due to limited non-destructive measurements, computationally demanding simulations, and inherent uncertainties in the system. We propose a two-step unsupervised deep learning framework named as Conditional Latent Autoregressive Recurrent Model (CLARM) for learning the spatiotemporal dynamics of charged particles in accelerators. CLARM consists of a Conditional Variational Autoencoder (CVAE) transforming six-dimensional phase space into a lower-dimensional latent distribution and a Long Short-Term Memory (LSTM) network capturing temporal dynamics in an autoregressive manner. The CLARM can generate projections at various accelerator modules by sampling and decoding the latent space representation. The model also forecasts future states (downstream locations) of charged particles from past states (upstream locations). The results demonstrate that the generative and forecasting ability of the proposed approach is promising when tested against a variety of evaluation metrics.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 32 of its 77 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

32 of 77 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  5. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  6. 2018Assessing Generative Models via Precision and Recallcited by 401
  7. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  8. 2021Enhancing Computational Fluid Dynamics with Machine Learningcited by 137
  9. 2014Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognitioncited by 111
  10. 2018Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flowcited by 97
  11. 2016Neural Autoregressive Distribution Estimationcited by 94
  12. 2020Multiscale Simulations of Complex Systems by Learning their Effective Dynamicscited by 86
20 more
  1. 2023β-Variational autoencoders and transformers for reduced-order modelling of fluid flowscited by 76
  2. 2018Molecular generative model based on conditional variational autoencoder for de novo molecular designcited by 73
  3. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  4. 2023Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generationcited by 51
  5. 2021Neural Point Process for Learning Spatiotemporal Event Dynamicscited by 42
  6. 2020Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3Dcited by 26
  7. 2020Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detectioncited by 20
  8. 2020Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial networkcited by 16
  9. 2020Superconducting radio-frequency cavity fault classification using machine learning at Jefferson Laboratorycited by 15
  10. 2020Physics-Based Deep Neural Networks for Beam Dynamics in Charged Particle Acceleratorscited by 7
  11. 2021High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networkscited by 7
  12. 2023Learning to Forecast Aleatoric and Epistemic Uncertainties over Long Horizon Trajectoriescited by 6
  13. 2021Neural network based order parameter for phase transitions and its applications in high-entropy alloyscited by 4
  14. 2021Adaptive Machine Learning for Time-Varying Systems: Low Dimensional Latent Space Tuningcited by 3
  15. 2022Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavitiescited by 3
  16. 2022Inverse characterization of composites using guided waves and convolutional neural networks with dual-branch feature fusioncited by 3
  17. 2023Physics-constrained 3D Convolutional Neural Networks for Electrodynamicscited by 3
  18. 2022Delamination prediction in composite panels using unsupervised-feature learning methods with wavelet-enhanced guided wave representationscited by 2
  19. 2023Experimental Safe Extremum Seeking for Acceleratorscited by 2
  20. 2022Towards deep generation of guided wave representations for composite materialscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 3.

7 papers.

  1. 2025MORPH: PDE Foundation Models with Arbitrary Data Modalitycited by 12
  2. 2024Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversalcited by 6
  3. 2024Classifier-pruned Bayesian optimization for particle accelerator tuning: Exploring temporally structured manifold of 6D beam phase spacecited by 1
  4. 2025Robust Anomaly Detection through Multi-Modal Autoencoder Fusion for Small Vehicle Damage Detectioncited by 1
  5. 2026Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loadingcited by 1
  6. 2026PDE foundation model-accelerated inverse estimation of system parameters in inertial confinement fusioncited by 1
  7. 2026Advancing accelerator virtual beam diagnostics through latent evolution modeling: an integrated solution to forward, inverse, tuning, and UQ problemscited by 0