4DMulti: automated multicomponent identification at complex material interfaces
Abstract
Mapping crystalline phases at heterogeneous interfaces is essential for understanding material performance and degradation. However, structural heterogeneity, phase overlap, and local disorder complicate diffraction interpretation, while growing data volumes make manual analysis increasingly impractical. We introduce 4DMulti, a physics-guided learning framework for automated multicomponent identification from large-scale four-dimensional scanning transmission electron microscopy (4D-STEM) data. The supporting diffraction data resource comprises over 6 million high-quality experimental patterns and labeled patterns generated by Sim2real. A retrieval-conditioned latent diffusion transformer (Sim2real) translates simulated patterns into experimental-style examples under constraints designed to preserve Bragg geometry, while a rotation-invariant coordinate convolutional network identifies phases across in-plane rotations. 4DMulti achieves 98.82% classification accuracy on a five-phase experimental nanoparticle benchmark, with ablation studies supporting the complementary benefits of domain adaptation and rotation-invariant classification. We define diffraction-inferred structural complexity (DISC), a normalized predictive entropy score that quantifies phase-assignment ambiguity within a specified candidate phase library. We apply 4DMulti to generate structural maps of superconducting heterostructures, corroded alloy surfaces, and degraded solid-state battery interfaces down to single-nanometer spatial resolution. 4DMulti connects simulation-derived crystallographic knowledge to automated experimental interpretation, establishing a foundation for scalable analysis of complex interfaces and data-driven discovery of interfacial design principles.
Related
- Edge energy fluctuation: A unified theory of friction scaling laws in twisted layered material interfaces
- Band Gaps and Localization of Surface Waves at Hyperbolic Material and Topological Insulator Interfaces
- Material chemical composition impacts on the band alignments: preliminary results on the 3D/2D perovskite interfaces
- Specimen design for material parameter identification using topology optimization
- Data-driven material data identification in micromorphic continua
BibTeX
@misc{zhang20264dmulti,
title = {{4DMulti: automated multicomponent identification at complex material interfaces}},
author = {Haoran Zhang and Zian Mao and Shufen Chu and Xiaoya He and Yuyan Guan and Antong Yang and Mingze Li and Xiaoqin Zeng and Yujun Xie},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.14348},
eprint = {2609.14348},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.14348},
}
RIS
TY - UNPB
TI - 4DMulti: automated multicomponent identification at complex material interfaces
AU - Haoran Zhang
AU - Zian Mao
AU - Shufen Chu
AU - Xiaoya He
AU - Yuyan Guan
AU - Antong Yang
AU - Mingze Li
AU - Xiaoqin Zeng
AU - Yujun Xie
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2609.14348
UR - https://arxiv.org/abs/2609.14348
AB - Mapping crystalline phases at heterogeneous interfaces is essential for understanding material performance and degradation. However, structural heterogeneity, phase overlap, and local disorder complicate diffraction interpretation, while growing data volumes make manual analysis increasingly impractical. We introduce 4DMulti, a physics-guided learning framework for automated multicomponent identification from large-scale four-dimensional scanning transmission electron microscopy (4D-STEM) data. The supporting diffraction data resource comprises over 6 million high-quality experimental patterns and labeled patterns generated by Sim2real. A retrieval-conditioned latent diffusion transformer (Sim2real) translates simulated patterns into experimental-style examples under constraints designed to preserve Bragg geometry, while a rotation-invariant coordinate convolutional network identifies phases across in-plane rotations. 4DMulti achieves 98.82% classification accuracy on a five-phase experimental nanoparticle benchmark, with ablation studies supporting the complementary benefits of domain adaptation and rotation-invariant classification. We define diffraction-inferred structural complexity (DISC), a normalized predictive entropy score that quantifies phase-assignment ambiguity within a specified candidate phase library. We apply 4DMulti to generate structural maps of superconducting heterostructures, corroded alloy surfaces, and degraded solid-state battery interfaces down to single-nanometer spatial resolution. 4DMulti connects simulation-derived crystallographic knowledge to automated experimental interpretation, establishing a foundation for scalable analysis of complex interfaces and data-driven discovery of interfacial design principles.
ER -