TY - CONF A1 - Radtke, Martin A1 - Cakir, Cafer Tufan A1 - de Oliveira Guilherme Buzanich, Ana T1 - Getting more efficient – The use of Bayesian optimization and Gaussian processes at the BAMline N2 - 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. In this paper, several examples in the areas of beamline alignment and measurement time optimization based on Bayesian optimization (BO) with Gaussian processes (GP) are presented. BO is a method for finding the global optimum of a function using a probabilistic model represented by a GP. The advantage of this method is that it can handle high-dimensional problems, does not depend on the initial estimate, and also provides uncertainty estimates. After a short introduction to BO and GP, the first example is the automatic alignment of our double multilayer monochromator (DMM). To achieve optimal performance, up to three linear and two angular motor positions have to be optimized. To achieve this with a grid scan, at least 100^5 measurement points would be required. Assuming that all positions can be aligned independently, 100*5 points are still necessary. We show that with BO and GP less than 100 points are sufficient to achieve equal or better results. The second example is the optimization of measurement time in XRF scanning. Here we will show the advantage of the BO GP approach over point-by-point scanning. As can be seen in Fig. 1, the number of points required and thus the measurement time can be reduced by a factor of 50, while the loss in image quality is acceptable. The advantages and limitations of this approach will be discussed. T2 - European Conference on X-ray Spectrometry 2022 CY - Bruges, Belgium DA - 26.06.2022 KW - Artificial Inelligence KW - Machine Learning KW - Bayesian Statistics KW - Gaussian process KW - Neural network KW - BAMline KW - Synchrotron PY - 2022 AN - OPUS4-56251 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin A1 - Cakir, Cafer Tufan A1 - de Oliveira Guilherme Buzanich, Ana T1 - Getting more efficient – The use of Bayesian optimization and Gaussian processes at the BAMline N2 - 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. T2 - SNI2022 conference CY - Berlin, Germany DA - 05.09.2022 KW - Artificial Inelligence KW - Machine Learning KW - Bayesian Statistics KW - Gaussian process KW - X-ray fluorescence KW - BAMline PY - 2022 AN - OPUS4-56255 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Fernandez-Poulussen, D. A1 - Hodoroaba, Vasile-Dan A1 - Drobne, D. A1 - Novak, S. A1 - Kranjc, E. A1 - Pellegrino, F. A1 - Gullumian, M. A1 - Jones, E. A1 - Hardy, B. A1 - Valsami-Jones, E. A1 - Jurkschat, K. A1 - van der Zande, M. T1 - Holistic, reliable and practical Characterization Framework for Graphene Family Materials, a correlated approach including Imaging based techniques N2 - ACCORDs is an Horizon Europe project working in the development of an imaging-based characterization framework (ACCORDs framework) for the holistic correlative assessment of Graphene Family Materials (GFMs) as a representative of 2D nanomaterials (NMs) to assess and predict 2D NMs health and environmental risks. The ACCORDs framework will operationalise safe and sustainable by design (SSbD) strategies proposed in past or ongoing H2020 projects or within OECD by correlating low-, medium-, and high-resolution physico-chemical-biological imaging-based methods with non-imaging methods in a tiered approach. ACCORDs will deliver the ACCORDs framework and user guidance, new imaging-based characterisation methods, reference in vitro tests, new reference 2D NMs for different matrices, a new minimum information reporting guideline for FAIR data sharing and reuse of images as well as an atlas with reference images for diagnostics of compromised safety of GFMs/GFM products. The new guidelines and standard proposals will be submitted to standardisation bodies to allow creation of regulatory ready products. The novelty of ACCORDs is in translating the principles of medical imaging-based diagnostics to 2D material hazard diagnostics. ACCORDs will accelerate industrial sectors in the area of aviation, marine construction, drone production, flexible electronics, photovoltaics, photocatalytics and print inks-based sensors. The value ACCORDs proposes to the graphene industry are practical, easy, imaging-based tools for GFM quality monitoring next to the production line with a possibility to be correlated with advanced highresolution imaging characterization methods in case hazard i.e. deviation from controls (benchmark values) are diagnosed. The ACCORDs framework and tools will contribute to the European Green Deal by addressing the topic: “Graphene: Europe in the lead” and to a new European strategy on standardization, released on 2nd February, 2022. T2 - MaterialsWeek 2024 CY - Limassol, Cyprus DA - 17.06.2024 KW - Graphene KW - Graphene-related 2D materials KW - SSbD KW - Imaging KW - ACCORDs PY - 2024 AN - OPUS4-60573 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Pauw, Brian Richard A1 - Hörmann, Anja A1 - Moradi, Melika A1 - Smales, Glen Jacob A1 - Breßler, Ingo A1 - Moeez, Abdul T1 - Laboratory x-ray scattering instruments as agile test-beds towards holistic experimentation N2 - Laboratory sources offer a unique advantage compared to synchrotron sources, largely in terms of freedom of operation. This freedom from user obligations, technology and software stacks and legacy decisions make the laboratory a very flexible place to develop and explore new ideas. The unparalleled availability furthermore allows for iterative improvement of instrumentation, sample environments and measurement methodologies to maximise the quality of the data obtained. This talk will highlight the use of the laboratory as an agile test-bed and development space, by giving examples of some complete and incomplete investigations undertaken in our laboratory over the last years. Furthermore, it will introduce the concept of holistic experimentation, where the laboratory provides broad-ranging support for materials science investigations. This means that we assist in the experimental preparation, perform the measurements, correction and analysis, and follow-up with assistance in interpretation of our analyses in light of the results from other techniques applied to the investigation. T2 - Invited talk at Diamond Light Source CY - Didcot, UK DA - 22.05.2024 KW - X-ray scattering KW - Methodology development KW - Laboratory management KW - Holistic experimentation KW - Laboratory automation KW - Nanostructural analysis PY - 2024 AN - OPUS4-60582 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Pauw, Brian Richard A1 - Smales, Glen Jacob A1 - Chambers, Aaron P. A. A1 - Hörmann, Anja A1 - Frontzek, Julius A1 - Du, Bofeng A1 - Breßler, Ingo T1 - Getting down to business: pragmatic solutions for laboratory automation N2 - A chemical engineer by training, Brian drifted towards physics and now focuses on a broad spectrum of activities with the aim to improve scientific reproducibility. This includes studies on holistically improving data quality, data collection efficiency and traceability, as well as concomitant laboratory automation for the preparation of consistent, well-documented sample series. The need for pragmatism led to an inexpensive, flexible laboratory automation platform that can be implemented in a modest amount of time. This talk presents that effort. T2 - Future Labs Live 2024 CY - Basel, Switzerland DA - 25.06.2024 KW - Laboratory automation KW - Experiment tracking KW - Holistic experimentation KW - Experimental traceability KW - Data visualisation KW - Parameter correlation. PY - 2024 AN - OPUS4-60583 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -