Dr. Andreas Dopp

Beam parameter optimization in accelerators involves multiple, sometimes competing, objectives. Condensing these individual objectives into a single figure of merit unavoidably results in a bias towards particular outcomes, often in an undesired way in the absence of prior knowledge. Finding an optimal objective definition then requires operators to iterate over many possible objective weights and definitions, a process that can take many times longer than the optimization itself. A more versatile approach is multi-objective optimization, which establishes the trade-off curve or Pareto front between objectives. Here we present the first results on multi-objective Bayesian optimization of a simulated laser-plasma accelerator. We find that multi-objective optimization reaches comparable performance to its single-objective counterparts while allowing for instant evaluation of entirely new objectives. This dramatically reduces the time required to find appropriate objective definitions for new problems. Additionally, our multi-objective, multi-fidelity method reduces the time required for an optimization run by an order of magnitude. It does so by dynamically choosing simulation resolution and box size, requiring fewer slow and expensive simulations as it learns about the Pareto-optimal solutions from fast low-resolution runs. The techniques demonstrated in this paper can easily be translated into many different computational and experimental use cases beyond accelerator optimization.

Laser-plasma physics has developed rapidly over the past few decades as lasers have become both more powerful and more widely available. Early experimental and numerical research in this field was dominated by single-shot experiments with limited parameter exploration. However, recent technological improvements make it possible to gather data for hundreds or thousands of different settings in both experiments and simulations. This has sparked interest in using advanced techniques from mathematics, statistics and computer science to deal with, and benefit from, big data. At the same time, sophisticated modeling techniques also provide new ways for researchers to deal effectively with situation where still only sparse data are available. This paper aims to present an overview of relevant machine learning methods with focus on applicability to laser-plasma physics and its important sub-fields of laser-plasma acceleration and inertial confinement fusion.

We present experimental results on a plasma wakefield accelerator (PWFA) driven by high-current electron beams from a laser wakefield accelerator (LWFA). In this staged setup stable and high-quality (low-divergence and low energy spread) electron beams are generated at an optically generated hydrodynamic shock in the PWFA. The energy stability of the beams produced by that arrangement in the PWFA stage is comparable to both single-stage laser accelerators and plasma wakefield accelerators driven by conventional accelerators. Simulations support that the intrinsic insensitivity of PWFAs to driver energy fluctuations can be exploited to overcome stability limitations of state-of-the-art laser wakefield accelerators when adding a PWFA stage. Furthermore, we demonstrate the generation of electron bunches with energy spread and divergence superior to single-stage LWFAs, resulting in bunches with dense phase space and an angular-spectral charge density beyond the initial drive beam parameters. These results unambiguously show that staged LWFA-PWFA can help to tailor the electron-beam quality for certain applications and to reduce the influence of fluctuating laser drivers on the electron-beam stability. This encourages further development of this new class of staged wakefield acceleration as a viable scheme toward compact, high-quality electron beam sources.

Beam parameter optimization in accelerators involves multiple, sometimes competing, objectives. Condensing these individual objectives into a single figure of merit unavoidably results in a bias towards particular outcomes, often in an undesired way in the absence of prior knowledge. Finding an optimal objective definition then requires operators to iterate over many possible objective weights and definitions, a process that can take many times longer than the optimization itself. A more versatile approach is multi-objective optimization, which establishes the trade-off curve or Pareto front between objectives. Here we present the first results on multi-objective Bayesian optimization of a simulated laser-plasma accelerator. We find that multi-objective optimization reaches comparable performance to its single-objective counterparts while allowing for instant evaluation of entirely new objectives. This dramatically reduces the time required to find appropriate objective definitions for new problems. Additionally, our multi-objective, multi-fidelity method reduces the time required for an optimization run by an order of magnitude. It does so by dynamically choosing simulation resolution and box size, requiring fewer slow and expensive simulations as it learns about the Pareto-optimal solutions from fast low-resolution runs. The techniques demonstrated in this paper can easily be translated into many different computational and experimental use cases beyond accelerator optimization.

Laser-plasma physics has developed rapidly over the past few decades as lasers have become both more powerful and more widely available. Early experimental and numerical research in this field was dominated by single-shot experiments with limited parameter exploration. However, recent technological improvements make it possible to gather data for hundreds or thousands of different settings in both experiments and simulations. This has sparked interest in using advanced techniques from mathematics, statistics and computer science to deal with, and benefit from, big data. At the same time, sophisticated modeling techniques also provide new ways for researchers to deal effectively with situation where still only sparse data are available. This paper aims to present an overview of relevant machine learning methods with focus on applicability to laser-plasma physics and its important sub-fields of laser-plasma acceleration and inertial confinement fusion.