Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach

2026-05-31

AI Summary

This work addresses the challenge of efficiently predicting emergent properties in vertically stacked two-dimensional (2D) heterostructures by proposing a multimodal deep learning approach—the first to introduce multimodal learning into bilayer 2D material systems. The method integrates atomic structures, stacking configurations, and interfacial information from individual constituent layers to enable end-to-end modeling of interlayer coupling effects and emergent physical properties. Leveraging high-throughput computational data and structural representation encoding, the model significantly outperforms existing methods across multiple benchmark tests, demonstrating superior accuracy and computational efficiency. This approach establishes a new paradigm for the rational design of 2D heterostructures with tailored functionalities.

Abstract

AI for materials science is a critical topic within AI for science, aiming to accelerate materials discovery and produce accurate property predictions. Bilayer 2D material stacking is essential for exploring new materials with novel functions and inherent phenomena, enabling the creation of new 2D bilayers for diverse real-world applications. Research on bilayer vdWs materials has made significant progress from experimental and computational perspectives. Various bilayer materials have been successfully synthe sized experimentally and the increasing utilization of high-throughput computing technology has con structed several computational two-dimensional materials databases. However, the use of AI to model bilayer stacking and predict new properties remains underexplored, necessitating further research studies. In this work, we propose a novel multimodal learning approach to study the interfaces between dissimilar materials that jointly enable new or multiple functions, and to predict new properties arising from the vertical integration (stacking) of different functional material layers under given configurations. Comprehensive experiments demonstrate the effectiveness and efficiency of our approach compared to baseline methods. Our code is available at https://github.com/AnVuong123/bimat ml.

Problem

• bilayer materials
• property prediction
• stacking
• multimodal learning
• 2D materials

Innovation

• multimodal learning
• bilayer 2D materials
• stacking configuration
• property prediction
• van der Waals heterostructures