Exploiting High Repetition Rate Experiments In Dynamic High-Pressure Physics.

我的项目将基于使用机器学习技术来分析由各种材料对基于激光的动态压缩的响应产生的x射线衍射图案，以高重复率执行。实验数据将使用欧洲的XFEL等设备产生。这些设备在飞秒时间尺度上产生类似激光的x射线束。这些高能脉冲被用来揭示材料在高压下如何变形。因此，这些实验可以用来揭示ICF胶囊早期压缩阶段的特征，探索行星核心材料的特性，并了解在高应变率机械故障时材料内部发生的过程。使用机器学习，我们的目标是快速分析这些实验的结果，目的是数据分析将跟上现在可能在新的XFEL设备上的高重复率。这将有希望引导实验获得更富有成效的参数和机制，探测到否则会被遗漏的物理现象，并大大减少低质量或失败的拍摄

My project will be based on using machine learning techniques to analyse X-ray diffraction patterns produced from the responses of a variety of materials to laser-based dynamic compression, performed at high repetition rates. The experimental data will be produced using facilities such as the European XFEL. These facilities produce laser-like X-ray beams on the femtosecond timescale. These energetic pulses are used to reveal how materials deform at high pressure. These experiments can therefore be used to reveal the characteristics of early compression stages of ICF capsules, explore properties of materials at the cores of planets, and understand the processes that take place within materials during high strain-rate mechanical failures. Using machine learning we aim to quickly analyse the results of these experiments, with the aim that data analysis will keep pace with the high repetition rates now possible on new XFEL devices. This will hopefully guide the experiments to more fruitful parameters and regimes, detecting physics that would otherwise be missed, as well as greatly reducing poor quality or failed shots