结合化学与成像条件，提升原子分辨电镜中缺陷分类准确率
Context-Aware Deep Learning for Defect Classification in Atomic-Resolution STEM
- 融合图像对比度与材料成分、束流能量等元数据进行学习
- 模拟数据准确率超98%，实验数据接近人类水平
- 减少94%后验熵，适合材料表征与多模态AI研究
人工智能正快速推动材料表征发展，但现有电子显微镜应用多仅依赖图像对比度，忽略影响成像的化学成分与实验条件。这一局限使缺陷分类存在根本歧义，相同对比度可能源于不同材料或成像参数。本文提出一种上下文感知学习框架，将图像对比度与描述成分、束流能量、探测器几何的元数据相结合。基于涵盖96种掺杂单层过渡金属二硫化物的约5500万张模拟图像块（共576种情形），实验证明，引入上下文变量可将原本病态的图像分类任务转化为物理基础明确的良定问题。该框架在模拟数据上准确率达98%以上，在实验数据上接近人类判断水平，后验熵降低94%。通过强调上下文关联而非模型复杂度，该方法实现图像对比度与化学及成像条件的物理对齐，支持可解释的缺陷判定，并为自主材料表征中的多模态人工智能提供通用路径。
原文摘要 · Abstract (English)
Artificial intelligence is rapidly advancing materials characterization, yet most applications in electron microscopy rely solely on image contrast, overlooking the chemical and experimental context that shapes image formation. This limitation makes defect classification inherently ambiguous, as similar contrasts can arise from different materials or imaging conditions. Here we develop a context-aware learning framework that integrates image-derived contrast with metadata describing composition, beam energy, and detector geometry. Using a systematically constructed dataset of ~55 million simulated patches spanning 576 cases across 96 doped monolayer transition-metal dichalcogenides, we show that conditioning on contextual variables transforms defect classification from an ill-posed image-only task into a well-posed, physically grounded problem. The framework achieves over 98% accuracy on simulations and near-human agreement on experimental data, with a 94% reduction in posterior entropy. By emphasizing contextual grounding over architectural complexity, this approach links experimental image contrast to the underlying chemical and imaging conditions, supporting physically grounded defect assignments and a general pathway toward multimodal AI models for autonomous materials characterization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。