% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Voelter:641395,
author = {Voelter, Constantin and Starostin, Vladimir and Lapkin,
Dmitrii and Munteanu, Valentin and Romodin, Mikhail and
Hylinski, Maik and Gerlach, Alexander and Hinderhofer,
Alexander and Schreiber, Frank},
title = {{B}enchmarking deep learning for automated peak detection
on {GIWAXS} data},
journal = {Journal of applied crystallography},
volume = {58},
number = {2},
issn = {0021-8898},
address = {Copenhagen},
publisher = {Munksgaard},
reportid = {PUBDB-2025-05056},
pages = {513 - 522},
year = {2025},
abstract = {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.},
cin = {DOOR ; HAS-User},
ddc = {540},
cid = {I:(DE-H253)HAS-User-20120731},
pnm = {6G3 - PETRA III (DESY) (POF4-6G3) / DFG project
G:(GEPRIS)390727645 - EXC 2064: Maschinelles Lernen: Neue
Perspektiven für die Wissenschaft (390727645) / DFG project
G:(GEPRIS)460248799 - DAPHNE4NFDI - DAten aus PHoton- und
Neutronen Experimenten für NFDI (460248799) / 05K19VTA -
Entwicklung einer kompakten Probenumgebung mit Spin-Coater
für in-situ Röntgenstreuung an PETRA III. (BMBF-05K19VTA)},
pid = {G:(DE-HGF)POF4-6G3 / G:(GEPRIS)390727645 /
G:(GEPRIS)460248799 / G:(DE-Ds200)BMBF-05K19VTA},
experiment = {EXP:(DE-H253)P-P08-20150101},
typ = {PUB:(DE-HGF)16},
doi = {10.1107/S1600576725000974},
url = {https://bib-pubdb1.desy.de/record/641395},
}