Generative Models for Crystalline Materials
Advanced Materials · 2026-03 · 38 (18)
DOI: 10.1002/adma.202523620 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Advanced Materials, online erschienen am 26.02.2026. Verfasst von Houssam Metni und 15 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Nanotechnology, Karlsruhe Institute of Technology, Karlsruhe, Germany. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 263 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Research Foundation, European Union, Bundesministerium für Bildung und Forschung.
Abstract (Originalsprache)
Understanding structure‐property relationships in materials is fundamental in condensed matter physics and materials science. Over the past few years, machine learning (ML) has emerged as a powerful tool for advancing this understanding and accelerating materials discovery. Early ML approaches primarily focused on constructing and screening large material spaces to identify promising candidates for various applications. More recently, research efforts have increasingly shifted toward generating crystal structures using end‐to‐end generative models. This review analyzes the current state of generative modeling for crystal structure prediction and de novo generation. It examines crystal representations, outlines the generative models used to design crystal structures, and evaluates their respective strengths and limitations. Furthermore, the review highlights experimental considerations for evaluating generated structures and provides recommendations for suitable existing software tools. Emerging topics, such as modeling disorder and defects, integration in advanced characterization, incorporating synthetic feasibility constraints, and model explainability are explored. Ultimately, this work aims to inform both experimental scientists looking to adapt suitable ML models to their specific circumstances and ML specialists seeking to understand the unique challenges related to inverse materials design and discovery.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Nanotechnology, Karlsruhe Institute of Technology, Karlsruhe, Germany.
- Institute of Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany.
- Department of Materials Science and Engineering, University of California, Berkeley, California, USA.
- Materials Sciences Division, Lawrence Berkeley National Laboratory, California, USA.
ORCID-Profile: Houssam Metni, Laura Ruple, Lauren N Walters, Luca Torresi, Jonas Teufel, Henrik Schopmans, Yumeng Zhang, Marlen Neubert, Yuri Koide, Kevin Steiner, Paul Link, Gerbrand Ceder, Pascal Friederich
Förderung
- German Research Foundation
- European Union
- Bundesministerium für Bildung und Forschung
- Helmholtz Association
- Bakar Institute of Digital Materials for the Planet
- Klaus Tschira Stiftung
- U.S. Department of Energy
- Deutsche Forschungsgemeinschaft
Zitieren
APA
Metni, H., Ruple, L., Walters, L. N., Torresi, L., Teufel, J., Schopmans, H., Östreicher, J., Zhang, Y., Neubert, M., Koide, Y., Steiner, K., Link, P., Bär, L., Petrova, M., Ceder, G., & Friederich, P. (2026). Generative Models for Crystalline Materials. Advanced Materials, 38(18). https://doi.org/10.1002/adma.202523620
Vancouver
Metni H, Ruple L, Walters LN, Torresi L, Teufel J, Schopmans H, et al. Generative Models for Crystalline Materials. Advanced Materials. 2026;38(18). doi:10.1002/adma.202523620
BibTeX
@article{Metni2026,
author = {Metni, Houssam and Ruple, Laura and Walters, Lauren N and Torresi, Luca and Teufel, Jonas and Schopmans, Henrik and Östreicher, Jona and Zhang, Yumeng and Neubert, Marlen and Koide, Yuri and Steiner, Kevin and Link, Paul and Bär, Lukas and Petrova, Mariana and Ceder, Gerbrand and Friederich, Pascal},
title = {Generative Models for Crystalline Materials},
journal = {Advanced Materials},
year = {2026},
volume = {38},
number = {18},
doi = {10.1002/adma.202523620}
}
EUVIMED