Search

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.

The Centre for Advanced Laser Applications in Garching, Germany, is home to the ATLAS-3000 multi-petawatt laser, dedicated to research on laser particle acceleration and its applications. A control system based on Tango Controls is implemented for both the laser and four experimental areas. The device server approach features high modularity, which, in addition to the hardware control, enables a quick extension of the system and allows for automated data acquisition of the laser parameters and experimental data for each laser shot. In this paper we present an overview of our implementation of the control system, as well as our advances in terms of experimental operation, online supervision and data processing. We also give an outlook on advanced experimental supervision and online data evaluation – where the data can be processed in a pipeline – which is being developed on the basis of this infrastructure.

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. [ABSTRACT FROM AUTHOR]