cond-mat.mtrl-sciNov 6, 2026

Graph representations of dislocation networks

Authors: Gaurav Lathiya, Markus Stricker

Organizations: Interdisciplinary Centre for Advanced Materials Simulation(ICAMS), Ruhr-Universität Bochum, Universitätstraße 150, Bochum, 44801, NRW, Bochum.

Abstract

The mechanical response of a crystal is governed by the evolving network of dislocations it contains, yet quantitatively linking the `state of that network' to its yield stress remains challenging. Here we represent the dislocation networks obtained from discrete dislocation dynamic simulation as graphs, using five distinct graph representations, characterize each network through a compact set of topological properties, and predict the yield stress from these graph properties and the applied strain rate using a standard random forest model evaluated with strain rate stratified cross-validation. The model predicts the yield stress with R2≈0.86−0.90R^2\approx0.86-0.90 across all box sizes and R2≈0.91−0.94R^2\approx0.91-0.94 for larger box sizes, and this accuracy is consistent across all five representations, indicating that the topology-stress relationship is a robust feature of the graph properties rather than an artefact of any single graph representation. We propose graph topology as a compact and robust route for connecting the microstructural state of a dislocation network to its mechanical response in addition to established variables.

Figures & tables

Explore similar work

CardsList
  1. Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks

    Jun 9, 2026Manuel Ricardo Guevara Garban, Yves Chemisky, Étienne Prulière +3Neural Surrogate ModelingStructural Mechanics

  2. Physics-Informed Graph Neural Networks to Reconstruct Local Fields Considering Finite Strain Hyperelasticity

    Jul 5, 2025Manuel Ricardo Guevara Garban, Yves Chemisky, Étienne Prulière +1Physics-Informed GNNsStructural Mechanics

  3. Physics-Informed Discovery of Yield Functions in Plasticity via Convex Neural Representations

    Jun 12, 2026Hyeonbin Moon, Donghyuk Cho, Jecheon Yu +2Parameter IdentifiabilityPhysics-Informed ML