AI 中文总结
DINO4DSTEM是一种自监督机器学习框架，可直接从4D-STEM原始衍射数据自动发现结构状态，无需人工标注或预定义类别，能定量表征复杂材料的结构，已成功应用于吲哚美辛结晶研究。
AI 中文摘要
采用4D-STEM的纳米衍射技术已成为材料研究中定量纳米尺度结构mapping的关键技术，但解释结构复杂材料的高维数据集仍是主要瓶颈。现有分析流程通常依赖结构模型、人工标注、预定义类别或样品特定的启发式规则，限制了其表征异质复杂材料的能力。本文提出DINO4DSTEM，一种自监督机器学习框架，可直接从原始衍射数据自动发现具有结构意义的状态。无需结构模型、人工标签、预定义类别数量或系统特定参数调优，该框架学习的表征能按衍射图的内在结构相似性进行组织，将大量低剂量测量数据转化为定量纳米尺度结构图。在不同数据集上，DINO4DSTEM始终能识别主导结构自由度，实现无人工监督的分割。我们将该框架应用于吲哚美辛（一种对电子束敏感的多域药物体系）的结晶研究，发现结晶度从部分有序的前驱体中产生，且覆盖连续的结构有序谱；绘制了发现的纳米尺度结构状态，定量揭示样品中有序度的演变。通过用通用自监督表征学习替代特定任务分析，DINO4DSTEM为复杂材料的定量纳米尺度结构mapping提供了广泛适用的框架，可在异质、对电子束敏感的体系中发现涌现的结构组织。
英文摘要
Nanodiffraction using 4D-STEM has become a key technique for quantitative nanoscale structural mapping in materials research, yet interpreting its high-dimensional datasets in structurally complex materials remains a major bottleneck. Existing analysis workflows typically rely on structural models, manual annotation, predefined classes, or sample-specific heuristics, limiting their ability to characterize heterogeneous complex materials. Here, we introduce DINO4DSTEM, a self-supervised machine learning framework that automatically discovers structurally meaningful states directly from raw diffraction data. Without structural models, manual labels, a predefined number of classes, or system-specific parameter tuning, the framework learns representations that organize diffraction patterns by their intrinsic structural similarities, transforming large collections of low-dose measurements into quantitative nanoscale structure maps. Across diverse datasets, DINO4DSTEM consistently identifies the dominant structural degrees of freedom, providing segmentation without human supervision. We applied the framework to the crystallization of indomethacin, a beam-sensitive, multidomain pharmaceutical system, revealing that crystallinity emerges from a partially ordered precursor and spans a continuous spectrum of structural order. The discovered nanoscale structural states are mapped to reveal the evolution of order across the specimen quantitatively. By replacing task-specific analysis with general self-supervised representation learning, DINO4DSTEM provides a broadly applicable framework for quantitative nanoscale structural mapping in complex materials, enabling the discovery of emergent structural organization in heterogeneous, beam-sensitive systems.
CommentsMain text: 17 pages, 6 figures. Includes Supplementary Information (14 pages, 20 supplementary figures). Code: https://github.com/DanielKhaykelson/dino-4dstem
