Data-driven inference of twin network dynamics: nucleation, co-nucleation, transmission, and incidental contacts

Martensitic phase transformations and twinning are key mechanisms for accommodating plasticity in a wide range of structural alloys. As deformation progresses, transformed domains (TD) interact to form networks with remarkable complexity, and the topology of these networks is expected to dictate the mechanical response of the host microstructure. To date, our understanding of TD network evolution is limited due to the interrelated mechanisms involved in network dynamics such as TD nucleation, transmission or arrest at grain boundaries, short-range interactions within grains, and incidental interactions across grain boundaries. To address this, we introduce a machine learning framework to predict the outcome to TD-grain boundary interactions using multilayer perceptrons. Applying this approach to twinning in Ti, we then leverage the trained model to virtually generate fingerprints of TD networks and explore the role of contact mechanisms on the evolution of network structure. The model predicts contact formation with high accuracy and reveals that in addition to geometric alignment, internal stresses must be included to accurately capture contact geometries in poorly aligned configurations. Further, by applying the model to the evolution of virtual networks, we demonstrate, for the microstructure studied, that incidental domain interactions play a major role in dictating the network morphology.

Authors

Institutions

Publication Details

Journal
npj Computational Materials
Published
2026-11-17
DOI
https://doi.org/10.1038/s41524-026-02343-z
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
NOV
article

Data-driven inference of twin network dynamics: nucleation, co-nucleation, transmission, and incidental contacts

Duncan A. Greeley, Paul Agbaje, Hi Tin Vo, Laurent Capolungo
npj Computational Materials
Machine Learning in Materials Science
article

Data-driven inference of twin network dynamics: nucleation, co-nucleation, transmission, and incidental contacts

Duncan A. Greeley, Paul Agbaje, Hi Tin Vo, Laurent Capolungo
article en

Abstract

Martensitic phase transformations and twinning are key mechanisms for accommodating plasticity in a wide range of structural alloys. As deformation progresses, transformed domains (TD) interact to form networks with remarkable complexity, and the topology of these networks is expected to dictate the mechanical response of the host microstructure. To date, our understanding of TD network evolution is limited due to the interrelated mechanisms involved in network dynamics such as TD nucleation, transmission or arrest at grain boundaries, short-range interactions within grains, and incidental interactions across grain boundaries. To address this, we introduce a machine learning framework to predict the outcome to TD-grain boundary interactions using multilayer perceptrons. Applying this approach to twinning in Ti, we then leverage the trained model to virtually generate fingerprints of TD networks and explore the role of contact mechanisms on the evolution of network structure. The model predicts contact formation with high accuracy and reveals that in addition to geometric alignment, internal stresses must be included to accurately capture contact geometries in poorly aligned configurations. Further, by applying the model to the evolution of virtual networks, we demonstrate, for the microstructure studied, that incidental domain interactions play a major role in dictating the network morphology.

npj Computational Materials
Los Alamos National Laboratory (US), University of Tennessee at Knoxville (US)
U.S. Department of Energy, National Nuclear Security Administration, Basic Energy Sciences, Los Alamos National Laboratory
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.

Laika access coming soon