Chemische Charakterisierung und Spurenanalytik
Filtern
Erscheinungsjahr
- 2022 (3)
Dokumenttyp
- Posterpräsentation (2)
- Vortrag (1)
Sprache
- Englisch (3)
Referierte Publikation
- nein (3)
Schlagworte
- Machine Learning (3) (entfernen)
Organisationseinheit der BAM
- 6 Materialchemie (3)
- 6.3 Strukturanalytik (3)
Eingeladener Vortrag
- nein (1)
In this talk an overview about artificial intelligence/machine learning applications @BAMline is given. In the first part, the use of neural networks for the quantification of XRF measurements and the decoding of coded-aperture measurements are shown. Then it is shown how Gaussian processes and Bayesian statistics can be used to achieve an optimal alignment of the set-up and in general for optimization of measurements.
Our aim is to develop a simple and inexpensive method for full field X-ray fluorescence imaging.We combine an energydispersive array detector with a coded aperture to obtain high resolut ion images. To obtain the information from the recorded image a reconstruction step is necessary. The reconstruction methods we have developed, were tested on simulated data and then applied to experimental data. The first tests were carried out at the BAMline @BESSY II. This method enables the simultaneous detection of multiple elements,which is important e.g. in the field of catalysis.
Getting more efficient – The use of Bayesian optimization and Gaussian processes at the BAMline
(2022)
For more than 20 years, BAM is operating the BAMline at the synchrotron BESSY II in Berlin Adlershof. During this time, the complexity of the setup and the amount of data generated have multiplied. To increase the effectiveness and in preparation for BESSY III, algorithms from the field of machine learning are increasingly used.
After a short introduction to BO and GP, the first example is the automatic alignment of our double multilayer monochromator (DMM).
The second example is the optimization of measurement time in XRF scanning.