view article
Figure 3
Example output of an optimization run using a simulated annealing optimiser and the Optuna framework. The loss is the average difference of the measured images in row one and the predictions of the neural network in row two. By minimizing this loss the offset between experiment and simulation is derived, which represents the position of the motors to achieve alignment. An example of this perfect alignment is shown with the manganese and oxygen components of the signal marked.

Journal logoJOURNAL OF
SYNCHROTRON
RADIATION
ISSN: 1600-5775
Volume 31| Part 4| July 2024| Pages 698-705
https://doi.org/10.1107/S1600577524003850
Follow J. Synchrotron Rad.
Sign up for e-alerts
E-alerts
Follow J. Synchrotron Rad. on Twitter
Twitter
Follow us on facebook
Facebook
Sign up for RSS feeds
RSS