Physics-aware ai maps atomic structures in complex materials interfaces
Multi4D: an end-to-end neural network for structural determination at complex material interfaces
Computer Vision and Pattern Recognition
Summary
Materials often fail or work differently because their tiny building blocks at interfaces are mixed or disordered, which is hard to see clearly. The authors created a smart computer program called Multi4D that looks at special microscope data and accurately figures out what those tiny structures are and where they are located. This program can also tell when the structures are unclear or complicated. It works on real materials like superconductors and batteries, helping people understand and improve them.
What this means in practice
- •For materials characterization teams: Generate detailed atomic-level maps of complex interfaces in advanced materials from experimental 4D-STEM data with minimal manual effort.
- •For industrial quality control teams: Automatically identify structural variations and degradation in functional materials to improve manufacturing and lifetime predictions.
Authors
Haoran Zhang, Zian Mao, Shufen Chu, Xiaoya He, Yuyan Guan, Antong Yang, Mingze Li, Xiaoqin Zeng, Yujun Xie
Abstract
Heterogeneous interfaces dictate the performance and degradation of functional materials, making it essential to link local structural variations with macroscopic failure mechanisms to guide future materials design. Yet structural heterogeneity, phase overlap, and local disorder produce highly convoluted diffraction signatures, making extended transition regions difficult to interpret at atomic resolution across large fields of view. Here, we introduce Multi4D, a physics-informed neural network framework for automated multi-component crystallographic identification using four-dimensional scanning transmission electron microscopy (4D-STEM). By combining a latent-space Diffusion Transformer for physics-constrained style translation with a rotation-invariant convolutional neural network for orientation-agnostic classification, this approach translates multi-components diffraction datasets into deterministic crystallographic maps with 98.82% accuracy. In addition, we introduce Diffraction-Inferred Structural Complexity as an information-theoretic entropy metric derived from classifier predictive uncertainty that quantifies local structural ambiguity. We apply Multi4D to generate high-fidelity structural maps of complex superconducting heterostructures, corroded alloy surfaces, and degraded solid-state battery interfaces down to single-nanometer spatial resolution. This framework establishes a statistically robust analytical paradigm for automated microscopy, facilitating both industrial quality control and the data-driven discovery of interfacial design principles.