TY - CONF A1 - Radtke, Martin A1 - Cakir, Cafer Tufan T1 - Big to Small - Getting Smarter@BAMline N2 - 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. T2 - Forschungsseminar Institut für Optik und Atomare Physik TU Berlin CY - Berlin, Germany DA - 25.10.2022 KW - Artificial Inelligence KW - Machine Learning KW - Bayesian Statistics KW - Gaussian process KW - Neural network KW - BAMline KW - Synchrotron PY - 2022 AN - OPUS4-56249 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin T1 - From Egypt to Hiddensee – Analysis of Gold with Synchrotron Radiation IV N2 - 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. T2 - Ringvorlesung Einführung in die Archäometrie CY - Berlin, Germany DA - 04.11.2022 KW - Synchrotron KW - BAMline KW - Bayesian Statistics KW - Gold KW - Röntgenfluoreszenz PY - 2022 AN - OPUS4-56252 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin T1 - News from the BAMline N2 - A presentation of recent measurements at the BAMline with focus on AI and ML applications T2 - Seminar: Strahlenphysikalische Anwendungen in Technik und Medizin CY - Vienna, Austria DA - 18.05.2022 KW - Synchrotron KW - BAMline KW - Bayesian Statistics KW - Gold KW - X-ray fluorescence PY - 2022 AN - OPUS4-56253 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin A1 - de Oliveira Guilherme Buzanich, Ana A1 - Reinholz, Uwe T1 - Das goldene Zeitalter war damals Analyse von Gold mit Synchrotronstrahlung N2 - 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. T2 - WISSENSCHAFT MIT WIRKUNG: Workshop Kulturguterhaltung – vom Dampfkessel zu Nanomaterialien CY - Berlin, Germany DA - 17.11.2021 KW - Gold KW - Synchrotron KW - Bernstorf KW - Nebra KW - XRF PY - 2021 AN - OPUS4-54139 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin T1 - Machine learning for direct quantification of XRF measurements N2 - 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. T2 - Seminar series: Artificial Intelligence applied to X-ray / synchrotron techniques CY - Online meeting DA - 24.06.2021 KW - Artificial intelligence KW - Machine learning KW - Synchrotron KW - XRF PY - 2021 AN - OPUS4-54140 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin A1 - de Oliveira Guilherme Buzanich, Ana A1 - Reinholz, Uwe A1 - Emmerling, Franziska T1 - Materials research with synchrotron radiation N2 - 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. T2 - INCT-FNA Symposium 2019 CY - Niteroi, Brazil DA - 27.05.2019 KW - Synchrotron KW - XRF KW - XANES KW - EXAFS KW - TXRF KW - Color X-ray Camera PY - 2019 AN - OPUS4-48897 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin T1 - Machine learning for direct quantification of XRF measurements N2 - 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. T2 - Denver X-ray Conference CY - Lombard, IL, USA DA - 05.08.2019 KW - Machine learning KW - Artificial intelligence KW - Neural network KW - XRF KW - Synchrotron PY - 2019 AN - OPUS4-48903 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin A1 - Reinholz, Uwe A1 - de Oliveira Guilherme Buzanich, Ana T1 - Trace element analysis with synchrotron radiation N2 - Trace elements are chemical elements whose concentration in a material is very low. The exact definition depends on the application and varies for example between 100 micrograms per gram in analytical chemistry and 1000 micrograms per gram in geology. The ability to detect trace elements fast and quantitatively is of great importance in many areas of science and technology. With its high brilliance and flexibility in the excitation conditions, synchrotron radiation is an ideal tool for detecting traces even in small sample quantities. In this contribution I will report about the use of X-ray fluorescence(XRF)for qualitative and quantitative element sensitiveanalysis. In addition to the fundamentals of XRF and its quantification methods, the advantages and problems of different geometries like e.g. microXRF, Total Reflection X-ray Fluorescence (TXRF)or Double Dispersive XRF (D²XRF) will be discussed. Practical examples from BAMline from the research fields of medicine, geology and archaeometry will complete the lecture. T2 - Denver X-Ray Conference CY - Online meeting DA - 03.08.2020 KW - Synchrotron KW - BAMline KW - XRF PY - 2020 AN - OPUS4-51890 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin T1 - Artificial intelligence for spectroscopy examples from BAMline N2 - 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. T2 - Seminar Strahlenphysikalische Anwendungen in Technik und Medizin CY - ATi Wien, Austria DA - 22.01.2020 KW - Machine learning KW - Natural language processing KW - Neural networks KW - Synchrotron KW - BAMline PY - 2020 AN - OPUS4-51891 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin T1 - Von Ägypten bis Hiddensee Analyse von Gold mit Synchrotronstrahlung III N2 - Gold ist eines der sieben schon im Altertum bekannten Metalle und wurde wg. seines Glanzes und seiner Seltenheit von alters her als Tauschmittel und zur Herstellung von Schmuck benutzt. Außerdem ist es einfach bearbeitbar und weitestgehend gegen chemische Einflüsse resistent. Die Untersuchungen von Gold mit synchrotronstrahlungsangeregter Röntgenfluoreszenzanalyse sind zerstörungsfrei und geben Auskunft über die in der untersuchten Probe vorhandenen chemischen Elemente. Bei den hier vorgestellten Untersuchungen an der BAMline stehen Fragestellungen wie Herkunft, Herstellungsverfahren und Zusammengehörigkeit von Goldfunden im Vordergrund. Die verschiedenen Fragestellungen werden an einer Reihe von Beispielen erläutert die vom Wikingerschatz aus Hiddensee über die Himmelsscheibe von Nebra bis hin zu Funden aus Ägypten langen. Der Fund von Bernstorf wird ausführlich diskutiert. T2 - Vorlesung FU Berlin Einführung in die Archäometrie CY - Berlin, Germany DA - 06.11.2020 KW - Synchrotron KW - BAMline KW - XRF KW - Gold KW - Archäometrie PY - 2020 AN - OPUS4-51893 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -