Transformer-based prediction of two-dimensional material electronic properties under elastic strain engineering

TL;DR

This paper introduces a Transformer-based surrogate model that accurately predicts electronic properties of 2D materials under strain, enabling efficient exploration of strain effects with interpretability.

Contribution

It presents a novel Transformer-based framework for multi-property prediction of 2D materials under strain, achieving DFT-level accuracy and interpretability.

Findings

Self-attention maps identify shear strain as key interaction center.

Model achieves mean absolute error of 0.0103 eV in bandgap prediction.

Attention-based models provide physically interpretable insights.

Abstract

Strain engineering provides a powerful route for tuning the electronic properties of two-dimensional (2D) materials, but exploring the full multidimensional strain space with density functional theory (DFT) is computationally prohibitive due to the nonlinear coupling between normal and shear components. In this work, we introduce a Transformer-based, multi-target surrogate model framework that achieves DFT-level bandgap prediction accuracy, reaching a mean absolute error of 0.0103 eV while retaining full interpretability through attention-weight analysis. The learned self-attention map consistently identifies shear strain as the interaction center that influences both bandgap and phonon stability, an insight not readily captured by classical feature-importance metrics. This work establishes attention-based architectures as physically interpretable surrogate models for multi-property prediction, offering a generalizable strategy for accelerating deep elastic strain engineering in materials informatics.