TY - CONF A1 - Radtke, Martin T1 - ChatGPT and EPICS: LLM-Enhanced Control Systems for Synchrotron Beamlines N2 - The BAMlineat BESSY II represents a hard X-ray spectroscopy facility enabling non-destructive analysis across diverse research areas like materials science, chemistry, biology, and cultural heritage studies. As a multipurpose beamline serving users from various disciplines, it underscores the necessity of adaptable and efficient control systems to maximize beamline utilization and scientific output. In this contribution, we detail the innovative integration of ChatGPT, OpenAI’s state-of-the-art Large Language Model (LLM), with the Experimental Physics and Industrial Control System (EPICS) which underpins the operational framework of the BAMline. This integration leverages the advanced natural language processing (NLP) capabilities of ChatGPT, presenting a revolutionary approach to beamline control that markedly simplifies user interaction. Through this, we facilitate a user-friendly pathway to executing complex experimental setups, eliminating the barrier imposed by conventional scripting languages and the often-challenging graphical user interfaces. This innovation promises to significantly streamline experimental workflows, thereby enhancing the efficiency of scientific research conducted at the beamline. Further enhancing this user-centric approach, we introduce an advanced graphical user interface (GUI) application. This novel application seamlessly melds the LLM’s NLP capabilities with EPICS, thereby enabling researchers to articulate experimental requirements through simple textual or voice commands. This interface interprets these commands to manipulate various beamline components, including but not limited to the Double Crystal Monochromator (DCM), Double Multilayer Monochromator (DMM), as well as various filters and slits. By parsing user input, extracting pertinent parameters, and generating a structured JSON object that reflects the desired device positions and experimental settings, the GUI application bridges the gap between complex control commands and intuitive user interactions. This advancement not only lowers the entry threshold for new users but also streamlines the operational workflow for experienced researchers. Looking ahead, we aim to extend the system to cover the entire experimental cycle, from setup to data analysis. Using LLMs, one could translate plain-language experiment descriptions into precise operational commands, revolutionizing the research process and making advanced scientific exploration more accessible to a wider community. T2 - International Conference on Synchrotron Radiation Instrumentation (SRI) CY - Hamburg, Germany DA - 26.08.2024 KW - Chatgpt KW - EPICS KW - BAMline KW - Synchrotron PY - 2024 AN - OPUS4-61700 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin T1 - Getting more efficient – The use of Bayesian optimization and Gaussian processes at the BAMline N2 - The BAMline, a beamline for material science research at BESSY II, has been operated by the Bundesanstalt für Materialforschung und -prüfung for over two decades. In the last few years, Bayesian optimization (BO) with Gaussian processes (GP) has been introduced as a transformative method in this setting. This contribution highlights the integration and impact of BO and GP in refining BAMline operations. We will explore the impact of integrating Bayesian methods, especially when combined with Gaussian processes, on the operational efficiency of the BAMline. Our discussion commences with an overview of the fundamental concepts of active learning and optimization. This is followed by an in-depth analysis of specific case studies, drawing on our direct experience with these innovative methods. For this our focus is on three key applications: Alignment of Optical Elements (DCM and DMM): The implementation of Bayesian optimization using Gaussian processes has revolutionized the alignment process for the Double Crystal Monochromator (DCM) and the Double Multilayer Monochromator (DMM). This approach greatly reduced manual effort and enhanced the efficiency and effectiveness of the alignment procedure. Optimal Spot Selection for Spatial Mapping in XRF Studies: In X-ray fluorescence (XRF) experiments, determining the most informative sampling spots is crucial. The introduction of BO, informed by GP, has significantly improved the selection process, especially in large or heterogeneous samples. This methodology ensures maximum information gain, optimizing the balance between comprehensive mapping and resource management. Selection of Optimal Energies for XANES Measurements in GEXANES Geometry: In the specific context of X-ray Absorption Near Edge Structure (XANES) studies using Grazing Exit (GEXANES) geometry, the Bayesian approach with Gaussian processes is now utilized to identify the most effective energy settings. This results in detailed spectral data acquired in a much shorter time. We also address challenges and limitations encountered during implementation. Additionally, the versatility of this approach in addressing a range of different research questions will be demonstrated. T2 - Machine Learning Conference for X-Ray and Neutron-Based Experiments CY - Garching bei München, Germany DA - 08.04.2024 KW - BAMline KW - Synchrotron KW - XRF KW - Bayes PY - 2024 AN - OPUS4-61703 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin T1 - Machine learning - Examples from BAM Line N2 - This talk explores applications of artificial intelligence in the field of spectroscopy, with a special focus on research conducted at BAMline. We begin with an overview of synchrotron radiation and its unique capabilities in material analysis. The first part of the talk will cover the integration of AI algorithms in quantifying X-ray fluorescence measurements, providing enhanced precision and efficiency in data analysis. Following this, we will examine the role of language models in spectroscopic research, showcasing how these tools can facilitate the control of complex experimental set-ups T2 - Analytical Academy CY - Berlin, Germany DA - 12.11.2024 KW - ChatGPT KW - Neural networks KW - XRF KW - Synchrotron KW - BAMline PY - 2024 AN - OPUS4-61698 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Dobosy, Péter A1 - Nguyen, Hoang Thi Phuong A1 - Záray, Gyula A1 - Streli, Christina A1 - Ingerle, Dieter A1 - Ziegler, Philipp A1 - Radtke, Martin A1 - de Oliveira Guilherme Buzanich, Ana A1 - Endrédi, Anett A1 - Fodor, Ferenc T1 - Effect of iodine species on biofortification of iodine in cabbage plants cultivated in hydroponic cultures N2 - Iodine is an essential trace element in the human diet because it is involved in the synthesis of thyroid hormones. Iodine deficiency affects over 2.2 billion people worldwide, making it a significant challenge to find plant-based sources of iodine that meet the recommended daily intake of this trace element. In this study, cabbage plants were cultivated in a hydroponic system containing iodine at concentrations ranging from 0.01 to 1.0 mg/L in the form of potassium iodide or potassium iodate. During the experiments, plant physiological parameters, biomass production, and concentration changes of iodine and selected microelements in different plant parts were investigated. In addition, the oxidation state of the accumulated iodine in root samples was determined. Results showed that iodine addition had no effect on photosynthetic efficiency and chlorophyll content. Iodide treatment did not considerably stimulate biomass production but iodate treatment increased it at concentrations less than 0.5 mg/L. Increasing iodine concentrations in the nutrient solutions increased iodine content in all plant parts; however, the iodide treatment was 2–7 times more efficient than the iodate treatment. It was concluded, that iodide addition was more favourable on the target element accumulation, however, it should be highlighted that application of this chemical form in nutrient solution decreased the concetrations of selected micoelement concentration comparing with the control plants. It was established that iodate was reduced to iodide during its uptake in cabbage roots, which means that independently from the oxidation number of iodine (+ 5, − 1) applied in the nutrient solutions, the reduced form of target element was transported to the aerial and edible tissues. KW - BAMline KW - XANES KW - Synchrotron KW - Lodine PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-608330 DO - https://doi.org/10.1038/s41598-024-66575-z VL - 14 IS - 1 SP - 1 EP - 12 PB - Springer Science and Business Media LLC AN - OPUS4-60833 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Huang, Junhao A1 - Klahn, Marcus A1 - Tian, Xinxin A1 - Bartling, Stephan A1 - Zimina, Anna A1 - Radtke, Martin A1 - Rockstroh, Nils A1 - Naliwajko, Pawel A1 - Steinfeldt, Norbert A1 - Peppel, Tim A1 - Grunwaldt, Jan‐Dierk A1 - Logsdail, Andrew J. A1 - Jiao, Haijun A1 - Strunk, Jennifer T1 - Fundamental Structural and Electronic Understanding of Palladium Catalysts on Nitride and Oxide Supports N2 - The nature of the support can fundamentally affect the function of a heterogeneous catalyst. For the novel type of isolated metal atom catalysts, sometimes referred to as single‐atom catalysts, systematic correlations are still rare. Here, we report a general finding that Pd on nitride supports (non‐metal and metal nitride) features a higher oxidation state compared to that on oxide supports (non‐metal and metal oxide). Through thorough oxidation state investigations by X‐ray absorption spectroscopy (XAS), X‐ray photoelectron spectroscopy (XPS), CO‐DRIFTS, and density functional theory (DFT) coupled with Bader charge analysis, it is found that Pd atoms prefer to interact with surface hydroxyl group to form a Pd(OH)x species on oxide supports, while on nitride supports, Pd atoms incorporate into the surface structure in the form of Pd−N bonds. Moreover, a correlation was built between the formal oxidation state and computational Bader charge, based on the periodic trend in electronegativity. KW - BAmline KW - XANES KW - Catalyst PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-608341 DO - https://doi.org/10.1002/anie.202400174 SN - 1433-7851 VL - 63 IS - 20 SP - 1 EP - 9 PB - Wiley AN - OPUS4-60834 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - de Oliveira Guilherme Buzanich, Ana A1 - Radtke, Martin A1 - Emmerling, Franziska ED - Rogge, Andreas ED - Meng, Birgit T1 - Exploring new materials for Green Intelligent Building - How can our BAMline help? N2 - In the scope of exploring and characterizing new materials related to Green Intelligent Building (GIB), we will provide an overview of the X-ray spectroscopy and diffraction analytical methods available at the BAMline /1/. and Myspot beamlines. These are two universal beamlines at the Berlin Synchrotron BESSY-II, where BAM has access and supervision role. Overarching electronic and structural properties at different time and length scales, such measurements enable a real-time characterization of materials properties. We will show-case in situ and ex situ deterioration and hydration studies on cement-based constructure materials. T2 - 11. Jahrestagung des DAfStb mit 63. Forschungskolloquium der BAM Green Intelligent Building CY - Berlin, Germany DA - 16.10.2024 KW - BAMline KW - Scope of exploring KW - Green intelligent building PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-612882 SN - 978-3-9818564-7-7 SP - 30 EP - 36 PB - Bundesanstalt für Materialforschung und -prüfung (BAM) CY - Berlin AN - OPUS4-61288 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Cakir, Cafer Tufan A1 - Bogoclu, Can A1 - Emmerling, Franziska A1 - Streli, Christina A1 - de Oliveira Guilherme Buzanich, Ana A1 - Radtke, Martin T1 - Machine learning for efficient grazing-exit x-ray absorption near edge structure spectroscopy analysis: Bayesian optimization approach N2 - In materials science, traditional techniques for analyzing layered structures are essential for obtaining information about local structure, electronic properties and chemical states. While valuable, these methods often require high vacuum environments and have limited depth profiling capabilities. The grazing exit x-ray absorption near-edge structure (GE-XANES) technique addresses these limitations by providing depth-resolved insight at ambient conditions, facilitating in situ material analysis without special sample preparation. However, GE-XANES is limited by long data acquisition times, which hinders its practicality for various applications. To overcome this, we have incorporated Bayesian optimization (BO) into the GE-XANES data acquisition process. This innovative approach potentially reduces measurement time by a factor of 50. We have used a standard GE-XANES experiment, which serve as reference, to validate the effectiveness and accuracy of the BO-informed experimental setup. Our results show that this optimized approach maintains data quality while significantly improving efficiency, making GE-XANES more accessible to a wider range of materials science applications. KW - Machine Learning KW - GE-XANES KW - Bayesian Optimization PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-603955 DO - https://doi.org/10.1088/2632-2153/ad4253 VL - 5 IS - 2 SP - 1 EP - 12 PB - IOP Publishing AN - OPUS4-60395 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Senges, Gene A1 - de Oliveira Guilherme Buzanich, Ana A1 - Lindič, Tilen A1 - Gully, Tyler A. A1 - Winter, Marlon A1 - Radtke, Martin A1 - Röder, Bettina A1 - Steinhauer, Simon A1 - Paulus, Beate A1 - Emmerling, Franziska A1 - Riedel, Sebastian T1 - Unravelling highly oxidized nickel centers in the anodic black film formed during the Simons process by in situ X-ray absorption near edge structure spectroscopy N2 - The electrofluorination after Simons has been used for the last century to produce everyday life materials. An in situ XANES investigation of the controversially debated black film apparent in the Simons process revealed high-valent nickel centers. KW - Synchrotron KW - BAMline KW - XANES PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-608366 DO - https://doi.org/10.1039/d3sc06081k SN - 2041-6520 VL - 15 IS - 12 SP - 4504 EP - 4509 PB - Royal Society of Chemistry (RSC) AN - OPUS4-60836 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Cancella, Erick Paiva A1 - de Paula Guarnieri, Guilherme A1 - de Sousa Amadeu, Nader A1 - Radtke, Martin A1 - Garcia, Rodrigo Henrique A1 - de Azevedo, Eduardo Ribeiro A1 - Cosentino, Ivana Conte A1 - Mascarenhas, Yvonne Primerano A1 - Nery, José Geraldo T1 - Synthesis and physicochemical characterization of a novel bismuth silicate templated by tetrapropylammonium bromide and polydiallyldimethylammonium chloride N2 - A bismuth silicate (BiSi-1) was hydrothermally synthesized using tetrapropylammonium bromide (TPA·Br) as the organic structure-directing agent and shown by multi-scale characterization to be distinct from known Bi–silicates. Powder X-ray diffraction is indexable with an orthorhombic metric (a = 23.234 Å, b = 17.109 Å, c = 3.897 Å), consistent with a highly anisotropic, possibly layered framework. High-resolution TEM/SAED reveals nanocrystalline, plate-like domains assembled into sub-micrometric aggregates with locally oriented lamellae; lattice fringes (0.27–0.32 nm) match the strongest XRD spacings. Solid-state NMR establishes a silica-rich network with a dominant Q4 population (77%) and minor Q3 (11%) and Q2 (12%) sites; the contact-time dependence of 1H to 29Si cross-polarization is consistent with increasing proximal-proton density from Q4 to Q2. Aging to 24 h sharpens the 29Si lineshape, while calcination progressively removes the OSDA and vicinal hydroxyls; at 750 °C, 29Si spectra indicate framework densification/rearrangement. XANES/EXAFS places bismuth predominantly as Bi3+ in an oxide-like environment with a pronounced Bi–O first shell and no detectable Bi⁰ or Bi–Br contributions. ICP–OES yields a reproducible Bi/Si atomic ratio of 1:3. Thermogravimetry shows stepwise desorption, dehydroxylation, and template removal, with thermal stability maintained to 750 °C. Nitrogen sorption confirms mesoporosity in the as-made and Soxhlet-extracted solids (the latter exhibiting the highest surface area), whereas high-temperature calcination reduces porosity. Collectively, BiSi-1 emerges as a nanocrystalline, anisotropic Bi–silicate whose connectivity, local Bi–O environment, and accessible texture are tunable by aging and post-treatments, positioning it as a promising platform for heterogeneous catalysis and environmental remediation. KW - 29Si NMR KW - Bismuth KW - Silicate PY - 2025 DO - https://doi.org/10.1007/s10853-025-11732-6 SN - 0022-2461 VL - 60 IS - 45 SP - 22615 EP - 22635 PB - Springer Science and Business Media LLC AN - OPUS4-64755 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Radtke, Martin T1 - ChatGPT and epics: LLM enhanced control systems for synchrotron Beamlines N2 - The presentation describes how large language models (LLMs) such as ChatGPT can be integrated with the EPICS control system to improve the automation and usability of synchrotron beamlines like the BAMline at BESSY II. It explains how LLMs can interpret natural language instructions, translate them into EPICS commands, and interact with experimental tools to perform complex tasks such as moving motors, running scans, or adjusting beamline components. The system, named P.E.T.E.R. (Performance Enhancing Technology for Experimental Research), supports features like multi-step reasoning, Python scripting, feedback loops, multilingual input, and voice control using OpenAI’s ChatGPT and Whisper. T2 - Workshop "BAM - Fraunhofer Materials LLM days" CY - Tübingen, Germany DA - 03.07.2025 KW - Chatgpt KW - LLM KW - EPICS KW - BAMline KW - Sanchrotron PY - 2025 AN - OPUS4-64478 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -