Multi-Objective Bayesian Active Learning for MeV-ultrafast electron diffraction
arXiv:2404.02268 · doi:10.1038/s41467-024-48923-9
Abstract
Ultrafast electron diffraction using MeV energy beams(MeV-UED) has enabled unprecedented scientific opportunities in the study of ultrafast structural dynamics in a variety of gas, liquid and solid state systems. Broad scientific applications usually pose different requirements for electron probe properties. Due to the complex, nonlinear and correlated nature of accelerator systems, electron beam property optimization is a time-taking process and often relies on extensive hand-tuning by experienced human operators. Algorithm based efficient online tuning strategies are highly desired. Here, we demonstrate multi-objective Bayesian active learning for speeding up online beam tuning at the SLAC MeV-UED facility. The multi-objective Bayesian optimization algorithm was used for efficiently searching the parameter space and mapping out the Pareto Fronts which give the trade-offs between key beam properties. Such scheme enables an unprecedented overview of the global behavior of the experimental system and takes a significantly smaller number of measurements compared with traditional methods such as a grid scan. This methodology can be applied in other experimental scenarios that require simultaneously optimizing multiple objectives by explorations in high dimensional, nonlinear and correlated systems.
References in corpus (15)
- Magic-angle graphene superlattices: a new platform for unconventional superconductivity
- On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning
- Light-Induced Charge Density Wave in LaTe
- Imaging the Photochemical Ring-Opening of 1,3-Cyclohexadiene by Ultrafast Electron Diffraction
- Bayesian optimization of a free-electron laser
- Universal phase dynamics in VO2 switches revealed by ultrafast operando diffraction
- Achieving 50 femtosecond resolution in MeV ultrafast electron diffraction with a double bend achromat compressor
- Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization
- Machine Learning for Orders of Magnitude Speedup in Multi-Objective Optimization of Particle Accelerator Systems
- Femtosecond compression dynamics and timing jitter suppression in a terahertz-driven electron bunch compressor
- Terahertz-based attosecond metrology of relativistic electron beams
- Multi-Objective Bayesian Optimization for Accelerator Tuning
- Ultrafast Relativistic Electron Nanoprobes
- Physics-informed Gaussian Process for Online Optimization of Particle Accelerators
- Bayesian Optimization Algorithms for Accelerator Physics