EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CrystalMELA : a new crystallographic machine learning platform for crystal system determination

Nicola Corriero iD, Rosanna Rizzi iD, Gaetano Settembre iD, Nicoletta Del Buono iD, Domenico Diacono iD

Journal of Applied Crystallography · 01.04.2023 · 56 (2) · 409-419

DOI: 10.1107/s1600576723000596 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Crystallography, online erschienen am 28.02.2023. Verfasst von Nicola Corriero und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Crystallography, CNR, Bari, Italy. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Determination of the crystal system and space group is the first step of crystal structure analysis. Often this turns out to be a bottleneck in the material characterization workflow for polycrystalline compounds, thus requiring manual interventions. This work proposes a new machine-learning (ML)-based web platform, CrystalMELA (Crystallography MachinE LeArning), for crystal systems classification. Two different ML models, random forest and convolutional neural network, are available through the platform, as well as the extremely randomized trees algorithm, available from the literature. The ML models learned from simulated powder X-ray diffraction patterns of more than 280 000 published crystal structures from organic, inorganic and metal–organic compounds and minerals which were collected from the POW_COD database. A crystal system classification accuracy of 70%, which improved to more than 90% when considering the Top-2 classification accuracy, was obtained in tenfold cross-validation. The validity of the trained models has also been tested against independent experimental data of published compounds. The classification options in the CrystalMELA platform are powerful, easy to use and supported by a user-friendly graphic interface. They can be extended over time with contributions from the community. The tool is freely available at https://www.ba.ic.cnr.it/softwareic/crystalmela/ following registration.

Schlagwörter

Stichwörter der Autor:innen

X-ray diffractioncrystal system determinationmachine learning web platform

Autor:innen und Institutionen

  • Institute of Crystallography, CNR, Bari, Italy.
  • Department of Mathematics, University of Bari Aldo Moro, Bari, Italy.
  • National Institute for Nuclear Physics, Bari, Italy.

ORCID-Profile: Nicola Corriero, Rosanna Rizzi, Gaetano Settembre, Nicoletta Del Buono, Domenico Diacono

Zitieren

APA

Corriero, N., Rizzi, R., Settembre, G., Del Buono, N., & Diacono, D. (2023). CrystalMELA : a new crystallographic machine learning platform for crystal system determination. Journal of Applied Crystallography, 56(2), 409-419. https://doi.org/10.1107/s1600576723000596

Vancouver

Corriero N, Rizzi R, Settembre G, Del Buono N, Diacono D. CrystalMELA : a new crystallographic machine learning platform for crystal system determination. Journal of Applied Crystallography. 2023;56(2):409-419. doi:10.1107/s1600576723000596

BibTeX
@article{Corriero2023,
  author = {Corriero, Nicola and Rizzi, Rosanna and Settembre, Gaetano and Del Buono, Nicoletta and Diacono, Domenico},
  title = {CrystalMELA : a new crystallographic machine learning platform for crystal system determination},
  journal = {Journal of Applied Crystallography},
  year = {2023},
  volume = {56},
  number = {2},
  pages = {409--419},
  doi = {10.1107/s1600576723000596}
}
Kostenlos starten →