Development and Applications of a Magnetism‐Aware General‐Purpose Atomic Cluster Expansion Potential for the Fe‐O‐H Ternary System

We develop and benchmark a general-purpose machine-learned interatomic potential for the Fe-O-H ternary system, based on the Atomic Cluster Expansion. Following our approach developed for the Fe-O system, magnetism is explicitly treated by the model in an Ising-like manner. This allows efficient incorporation of magnetic degrees of freedom, making the potential applicable to large-scale atomistic calculations. We demonstrate the capability of the model to accurately describe a wide range of properties and capture basic mechanisms underlying hydrogen-based reduction of iron oxides, interaction of water with iron and hydrogen embrittlement of metallic iron.

Authors

Institutions

Publication Details

Journal
Advanced Science
Published
2026-07-27
DOI
https://doi.org/10.1002/advs.76709
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Development and Applications of a Magnetism‐Aware General‐Purpose Atomic Cluster Expansion Potential for the Fe‐O‐H Ternary System

Mira Todorova, Jörg Neugebauer, Ralf Drautz, Matous Mrovec et al.
Advanced Science
Machine Learning in Materials Science
article

Development and Applications of a Magnetism‐Aware General‐Purpose Atomic Cluster Expansion Potential for the Fe‐O‐H Ternary System

Mira Todorova, Jörg Neugebauer, Ralf Drautz, Matous Mrovec, Baptiste Bienvenu, Dierk Raabe
article en

Abstract

We develop and benchmark a general-purpose machine-learned interatomic potential for the Fe-O-H ternary system, based on the Atomic Cluster Expansion. Following our approach developed for the Fe-O system, magnetism is explicitly treated by the model in an Ising-like manner. This allows efficient incorporation of magnetic degrees of freedom, making the potential applicable to large-scale atomistic calculations. We demonstrate the capability of the model to accurately describe a wide range of properties and capture basic mechanisms underlying hydrogen-based reduction of iron oxides, interaction of water with iron and hydrogen embrittlement of metallic iron.

Advanced Science
Max-Planck-Institut für Nachhaltige Materialien (DE), Ruhr University Bochum (DE)
Alexander von Humboldt-Stiftung, European Commission, Deutsche Forschungsgemeinschaft
Peace, Justice and strong institutions
Openalex Percentile: Top 20%
Machine Learning in Materials Science
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.