Chemische Charakterisierung und Spurenanalytik
Filtern
Dokumenttyp
- Vortrag (19) (entfernen)
Referierte Publikation
- nein (19)
Schlagworte
- Synchrotron (19) (entfernen)
Organisationseinheit der BAM
- 6 Materialchemie (19) (entfernen)
Eingeladener Vortrag
- nein (19)
Various applications for artificial intelligence in the context of spectroscopy will be presented. in particular, examples from bamline will be featured. After a short introduction to synchrotron radiation, artificial intelligence algorithms for the quantification of X-ray fluorescence measurement are discussed. In the second example, information retrieval by natural language processing is reviewed. As a last example the reconstruction of measurements with the X-ray color camera and coded apertures is presented.
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.
Gold ist eines der sieben bereits in der Antike bekannten Metalle und wurde wegen seines Glanzes und seiner Seltenheit seit jeher als Tauschmittel und zur Herstellung von Schmuck verwendet. Außerdem ist es leicht zu bearbeiten und weitgehend resistent gegen chemische Einflüsse.
Die Analyse von Gold mit der durch Synchrotronstrahlung angeregten Röntgenfluoreszenzanalyse ist zerstörungsfrei und liefert Informationen über die in der untersuchten Probe vorhandenen chemischen Elemente.
Im Mittelpunkt der hier vorgestellten Untersuchungen an der BAMline stehen Fragen nach der Herkunft, dem Herstellungsprozess und der Zugehörigkeit von Goldfunden. Die verschiedenen Fragestellungen werden anhand einer Reihe von Beispielen erläutert, die vom Wikingerschatz von Hiddensee über die Himmelsscheibe von Nebra bis hin zu Funden aus Ägypten reichen. Darüber hinaus werden die heute am Synchrotron verfügbaren modernen Messmethoden vorgestellt.
Gold is one of the seven metals already known in antiquity and was used from time immemorial as a medium of exchange and for the production of jewelry because of its luster and rarity. In addition, it is easy to work and largely resistant to chemical influences. Investigations of gold using synchrotron radiation excited X-ray fluorescence analysis are non-destructive and provide information about the chemical elements present in the sample under investigation. The investigations presented here at BAMline focus on questions such as the origin, manufacturing process, and association of gold findings. The different questions are explained by a number of examples ranging from the Viking treasure from Hiddensee to the Nebra Sky Disk and finds from Egypt. The find from Bernstorf is discussed in detail. A Bayesian treatment of the authenticity is shown.
This contribution provides an overview of the BAMline synchrotron radiation beamline, which specializes in hard X-ray spectroscopy techniques for materials research. The BAMline offers X-ray absorption spectroscopy (XAS), x-ray fluorescence spectroscopy (XRF), and tomography to study materials' electronic structure, chemical composition, and structure. Key capabilities include standard and dispersive XAS for electronic structure, micro-XRF for elemental mapping, coded aperture imaging, and depth-resolved grazing exit XAS. The BAMline enables in situ characterization during materials synthesis and functions for energy, catalysis, corrosion, biology, and cultural heritage applications.
Ongoing developments like the implementation of machine learning techniques for experiment optimization and data analysis will be discussed. For instance, Bayesian optimization is being used to improve beamline alignment and scanning. An outlook to the future, where the BAMline will continue pioneering dynamic and multi-scale characterization, aided by advanced data science methods, to provide unique insights into materials research, will be given.
In this talk I’ll describe the use of artificial neural networks (ANN) for quantifying X-ray fluorescence (XRF) measurements. The main idea of this talk is to give an overview of the process needed to generate a model that can then be applied to a specific problem.
In XRF, a sample is excited with X-rays and the resulting characteristic radiation is detected to determine elements quantitatively and qualitatively. This is traditionally done in several time-consuming steps. I’ll show the possibilities and problems of using a neural network to realise a "one-click" quantification. This includes generating training data using Monte Carlo simulation and augmenting the existing data set with an ANN to generate more data. The search for the optimal hyperparameters, manually and automatically, is also described. For the case presented, we were able to train a network with a mean absolute error of 0.1% by weight for the synthetic data and 0.7% by weight for a set of experimental data obtained with certified reference materials.
In X-ray fluorescence (XRF), a sample is excited with X-rays, and the resulting characteristic radiation is detected to detect elements quantitatively and qualitatively. Quantification is traditionally done in several steps:
1. Normalization of the data
2. Determination of the existing elements
3. Fit of the measured spectrum
4. Calculation of concentrations with fundamental parameters / MC simulations / standard based
The problem with standard based procedures is the availability of corresponding standards. The problem with the calculations is that the measured intensities for XRF measurements are matrix-dependent. Calculations must, therefore, be performed iteratively (= time consuming) in order to determine the chemical composition.
First experiments with gold samples have shown the feasibility of machine learning based quantification in principle. A large number of compositions were simulated (> 10000) and analyzed with a deep learning network. For first experiments, an ANN (Artificial Neural Network) with 3 hidden layers and 33x33x33 neurons was used. This network learned the mapping of spectra to concentrations using supervised learning by multidimensional regression. The input layer was formed by the normalized spectrum, and the output layer directly yielded the searched values. The applicability for real samples was shown by measurements on certified reference materials.
Various applications for artificial intelligence in the context of spectroscopy will be presented. in particular, examples from BAMline will be presented. After a short introduction to synchrotron radiation, artificial intelligence algorithms for the quantification of X-ray fluorescence measurement are discussed. In the second example, information retrieval by natural language processing is discussed.
Synchrotron radiation sources with their unique properties in terms of intensity, polarization and adjustability offer a wide range of possibilities in materials research. A basic introduction about the creation and special properties of synchrotron radiation will be given. Examples of current work at BAMline, the high-energy measuring facility of the Federal Institute for Materials Research and Testing at the synchrotron BESSY, are used to illustrate the possibilities and limitations of existing measuring methods. It will be shown how the formation of corrosion layers can be tracked, how the abrasion of implants leads to the introduction of heavy metals into the surrounding bone matrix and how the detection of smallest impurities in gold is possible by optimizing the measuring conditions. Finally, an outlook at the hardware and software developments to be expected in the coming years is given.