Constantin Völter
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Constantin Völter has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Hinderhofer
University of Tübingen
4 shared publications - Dmitry Lapkin
Institute of Applied Physics – University of Tübingen, Auf der Morgenstelle 10, 72076 Tübingen, Germany
4 shared publications - Frank Schreiber
Institut für Angewandte Physik, Universität Tübingen, 72076 Tübingen, Germany
4 shared publications - Mikhail Romodin
Institute of Applied Physics – University of Tübingen, Auf der Morgenstelle 10, 72076 Tübingen, Germany
4 shared publications - Ainur F. Abukaev
Institut für Angewandte Physik Universität Tübingen Tübingen Germany
2 shared publications - Ekaterina Kneschaurek
University of Tübingen
2 shared publications
Latest Publications
- Open Access
- 17 June 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (4) , 045021
Automated peak detection in grazing-incidence diffraction using transformers
The adoption of grazing-incidence wide-angle X-ray scattering (GIWAXS) has expanded rapidly, as it has proven invaluable for extracting a wealth of structural information from thin films and surfaces on the atomic and molecular scale. The amount of scattering data collected in such experiments creates new challenges associated with relatively slow conventional data analysis due to the need for human input. Existing Machine-Learning-based Bragg-peak detection approaches have demonstrated the potential of automation, but significant challenges such as weak peaks, peaks on top of Debye-Scherrer rings, and difficulties in differentiating closely spaced peaks remain. We introduce a powerful model for GIWAXS peak detection based on a visual transformer that achieves a performance strongly surpassing existing models. We evaluate our new approach using a diverse set of labelled, experimental GIWAXS patterns from perovskite and organic thin films. Notably, we demonstrate for the first time the reliable detection of Bragg peaks superimposed on other peaks and Debye-Scherrer rings, a significant improvement in detecting low-intensity peaks and a substantially stronger overall performance. In addition, we evaluate both pre-and postprocessing latency, confirming that the overall analysis speed is sufficient for real-time applications. With its ability to deliver a fast and high-performance analysis, our approach enables new types of GIWAXS measurements, including closed-loop experiments, that were previously limited by analysis bottlenecks. The studied model could potentially also be applied to other datasets with a large dynamic range and weak signal-to-noise ratio.
- 17 June 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (4) , 045021
Open AccessAutomated peak detection in grazing-incidence diffraction using transformers
The adoption of grazing-incidence wide-angle X-ray scattering (GIWAXS) has expanded rapidly, as it has proven invaluable for extracting a wealth of structural information from thin films and surfaces on the atomic and molecular scale. The amount of scattering data collected in such experiments creates new challenges associated with relatively slow conventional data analysis due to the need for human input. Existing Machine-Learning-based Bragg-peak detection approaches have demonstrated the potential of automation, but significant challenges such as weak peaks, peaks on top of Debye-Scherrer rings, and difficulties in differentiating closely spaced peaks remain. We introduce a powerful model for GIWAXS peak detection based on a visual transformer that achieves a performance strongly surpassing existing models. We evaluate our new approach using a diverse set of labelled, experimental GIWAXS patterns from perovskite and organic thin films. Notably, we demonstrate for the first time the reliable detection of Bragg peaks superimposed on other peaks and Debye-Scherrer rings, a significant improvement in detecting low-intensity peaks and a substantially stronger overall performance. In addition, we evaluate both pre-and postprocessing latency, confirming that the overall analysis speed is sufficient for real-time applications. With its ability to deliver a fast and high-performance analysis, our approach enables new types of GIWAXS measurements, including closed-loop experiments, that were previously limited by analysis bottlenecks. The studied model could potentially also be applied to other datasets with a large dynamic range and weak signal-to-noise ratio.
- Open Access
- 1 February 2026
- Published by International Union of Crystallography (IUCr) in Journal of Applied Crystallography
- Vol. 59 (1) , 263-275
pygid : a Python package for fast data reduction in grazing-incidence diffraction
Advances in X-ray and neutron sources, as well as in area-detector technologies, enable the recording of several terabytes of raw two-dimensional detector data in a single experiment. While several efficient integration and conversion tools are available for data collected in transmission geometry, analogous solutions for grazing-incidence diffraction (including grazing-incidence X-ray diffraction and grazing-incidence wide-angle X-ray scattering) experiments have not yet achieved the same level of efficiency. The development of new data analysis tools, including machine-learning-based software for X-ray data, necessitates the establishment of a standardized format for the converted data. To address these challenges, we have developed a new Python library, pygid , which is designed to facilitate fast data processing while providing compatibility with various raw data formats, a standardized data storage format and an intuitive interface for straightforward use. pygid supports three types of coordinate systems and both transmission and grazing-incidence geometries. It is capable of handling large datasets, performing one-dimensional line cuts and simulating expected Bragg peak positions for given structures. The package facilitates sample and experimental metadata curation in accordance with the FAIR principles. As an integral part of the broader mlgid pipeline, pygid serves as the initial step linking raw scattering patterns with machine learning tools for data analysis. The pygid package is accessible at https://github.com/mlgid-project.
- 1 February 2026
- Published by International Union of Crystallography (IUCr) in Journal of Applied Crystallography
- Vol. 59 (1) , 263-275
Open Accesspygid : a Python package for fast data reduction in grazing-incidence diffraction
Advances in X-ray and neutron sources, as well as in area-detector technologies, enable the recording of several terabytes of raw two-dimensional detector data in a single experiment. While several efficient integration and conversion tools are available for data collected in transmission geometry, analogous solutions for grazing-incidence diffraction (including grazing-incidence X-ray diffraction and grazing-incidence wide-angle X-ray scattering) experiments have not yet achieved the same level of efficiency. The development of new data analysis tools, including machine-learning-based software for X-ray data, necessitates the establishment of a standardized format for the converted data. To address these challenges, we have developed a new Python library, pygid , which is designed to facilitate fast data processing while providing compatibility with various raw data formats, a standardized data storage format and an intuitive interface for straightforward use. pygid supports three types of coordinate systems and both transmission and grazing-incidence geometries. It is capable of handling large datasets, performing one-dimensional line cuts and simulating expected Bragg peak positions for given structures. The package facilitates sample and experimental metadata curation in accordance with the FAIR principles. As an integral part of the broader mlgid pipeline, pygid serves as the initial step linking raw scattering patterns with machine learning tools for data analysis. The pygid package is accessible at https://github.com/mlgid-project.
- Open Access
- 9 November 2025
- Published by The Open Journal in Journal of Open Source Software
- Vol. 10 (115) , 8499
mlgidGUI - an annotation program for 2D scattering data
- 9 November 2025
- Published by The Open Journal in Journal of Open Source Software
- Vol. 10 (115) , 8499
Open AccessmlgidGUI - an annotation program for 2D scattering data
- Open Access
- 28 February 2025
- Published by International Union of Crystallography (IUCr) in Journal of Applied Crystallography
- Vol. 58 (2) , 513-522
Benchmarking deep learning for automated peak detection on GIWAXS data
Recent advancements in X-ray sources and detectors have dramatically increased data generation, leading to a greater demand for automated data processing. This is particularly relevant for real-time grazing-incidence wide-angle X-ray scattering (GIWAXS) experiments which can produce hundreds of thousands of diffraction images in a single day at a synchrotron beamline. Deep learning (DL)-based peak-detection techniques are becoming prominent in this field, but rigorous benchmarking is essential to evaluate their reliability, identify potential problems, explore avenues for improvement and build confidence among researchers for seamless integration into their workflows. However, the systematic evaluation of these techniques has been hampered by the lack of annotated GIWAXS datasets, standardized metrics and baseline models. To address these challenges, we introduce a comprehensive framework comprising an annotated experimental dataset, physics-informed metrics adapted to the GIWAXS geometry and a competitive baseline – a classical, non-DL peak-detection algorithm optimized on our dataset. Furthermore, we apply our framework to benchmark a recent DL solution trained on simulated data and discover its superior performance compared with our baseline. This analysis not only highlights the effectiveness of DL methods for identifying diffraction peaks but also provides insights for further development of these solutions.
- 28 February 2025
- Published by International Union of Crystallography (IUCr) in Journal of Applied Crystallography
- Vol. 58 (2) , 513-522
Open AccessBenchmarking deep learning for automated peak detection on GIWAXS data
Recent advancements in X-ray sources and detectors have dramatically increased data generation, leading to a greater demand for automated data processing. This is particularly relevant for real-time grazing-incidence wide-angle X-ray scattering (GIWAXS) experiments which can produce hundreds of thousands of diffraction images in a single day at a synchrotron beamline. Deep learning (DL)-based peak-detection techniques are becoming prominent in this field, but rigorous benchmarking is essential to evaluate their reliability, identify potential problems, explore avenues for improvement and build confidence among researchers for seamless integration into their workflows. However, the systematic evaluation of these techniques has been hampered by the lack of annotated GIWAXS datasets, standardized metrics and baseline models. To address these challenges, we introduce a comprehensive framework comprising an annotated experimental dataset, physics-informed metrics adapted to the GIWAXS geometry and a competitive baseline – a classical, non-DL peak-detection algorithm optimized on our dataset. Furthermore, we apply our framework to benchmark a recent DL solution trained on simulated data and discover its superior performance compared with our baseline. This analysis not only highlights the effectiveness of DL methods for identifying diffraction peaks but also provides insights for further development of these solutions.
- Open Access
- 1 January 2024
- Published by HICSS Conference Office
Don't Buy the Pig in a Poke: Benchmarking DNNs Inference Performance before Development
As deep neural networks (DNNs) are increasingly used in practical settings, developers often adopt pre-existing DNN architectures from a vast collection of well-established models. However, in industrial environments, factors beyond simply achieving high accuracy are becoming important. The runtime performance is critical, as delays can lead to conveyor stops or equipment damage. Currently, determining the runtime performance of a DNN requires multiple iterations and testing specific configurations, whereas existing methods for benchmarking DNNs mainly compare different hardware or runtime parameters. We present tritonPerf, an approach to obtain and compare the runtime (latency and throughput) for a broad range of settings and existing DNN architectures in the final application environment. It allows data scientists to evaluate the performance and compare the results for a wide range of models before time and resource-intensive hyperparameter tuning is performed. We demonstrate the gain of tritonPerf in an extensive field study using an industrial setting, where we benchmark and compare the runtime of 57 different models.
- 1 January 2024
- Published by HICSS Conference Office
Open AccessDon't Buy the Pig in a Poke: Benchmarking DNNs Inference Performance before Development
As deep neural networks (DNNs) are increasingly used in practical settings, developers often adopt pre-existing DNN architectures from a vast collection of well-established models. However, in industrial environments, factors beyond simply achieving high accuracy are becoming important. The runtime performance is critical, as delays can lead to conveyor stops or equipment damage. Currently, determining the runtime performance of a DNN requires multiple iterations and testing specific configurations, whereas existing methods for benchmarking DNNs mainly compare different hardware or runtime parameters. We present tritonPerf, an approach to obtain and compare the runtime (latency and throughput) for a broad range of settings and existing DNN architectures in the final application environment. It allows data scientists to evaluate the performance and compare the results for a wide range of models before time and resource-intensive hyperparameter tuning is performed. We demonstrate the gain of tritonPerf in an extensive field study using an industrial setting, where we benchmark and compare the runtime of 57 different models.