In free-electron lasers (FELs), X-ray pulses are generated from spontaneous undulator radiation from electrons. This causes shot-to-shot fluctuations in the intensity, pointing, and spatial profile of the X-ray beam. In this work, we use deep neural networks to analyze X-ray images, enabling us to obtain statistical information of this intrinsically stochastic process. A supervised is built to classify X-ray images, and an unsupervised model is built to study the distribution of beam profiles.
Higher-order modes at FELs: A machine interpretation
Sun P.;
2019
Abstract
In free-electron lasers (FELs), X-ray pulses are generated from spontaneous undulator radiation from electrons. This causes shot-to-shot fluctuations in the intensity, pointing, and spatial profile of the X-ray beam. In this work, we use deep neural networks to analyze X-ray images, enabling us to obtain statistical information of this intrinsically stochastic process. A supervised is built to classify X-ray images, and an unsupervised model is built to study the distribution of beam profiles.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
