原子力显微镜
压扁
深度学习
计算机科学
人工智能
纳米尺度
纳米技术
一般化
表征(材料科学)
合成数据
特征(语言学)
显微镜
材料科学
操作员(生物学)
实验数据
机器学习
比例(比率)
可靠性(半导体)
人工神经网络
数据驱动
特征工程
卷积神经网络
特征提取
不确定度量化
能量(信号处理)
生物系统
作者
Rubén Millán‐Solsona,Martí Checa,Spenser R. Brown,Amber N. Bible,Bernadeta Srijanto,Laura Wiggins,Sita Sirisha Madugula,Alice L. B. Pyne,Jennifer L. Morrell‐Falvey,Scott T. Retterer,Rama Krishnan Vasudevan,Liam F. Collins
标识
DOI:10.1038/s41467-026-70421-3
摘要
Atomic force microscopy (AFM) is a widely used tool for nanoscale characterization across materials science, energy research, and biology. However, its adoption in high-throughput materials discovery and statistically driven studies remains limited by a strong dependence on expert operator input and by the scarcity of annotated experimental AFM datasets needed to enable data-driven automation. Here, we introduce SimuScan, a synthetic-data-driven framework that enables reliable AFM feature identification, segmentation, and targeted imaging without requiring large manually labeled experimental datasets. SimuScan generates tunable, high-fidelity synthetic AFM images of defined morphologies while incorporating realistic experimental artifacts, including tip-sample convolution, noise, flattening distortions, and surface debris. These datasets are shown to support scalable, label-free training of modern deep learning models for AFM analysis. When integrated into data-driven AFM workflows, SimuScan-trained models can locate and analyze nanoscale structures across large datasets and guide targeted follow-up imaging. We validate this approach on nanostructured surfaces, DNA assemblies, and bacterial cells, demonstrating robust generalization across diverse sample types with minimal operator intervention. More broadly, this work establishes a general strategy for generating explicitly conditioned, task-relevant synthetic data to improve the reliability of downstream models in autonomous microscopy.
科研通智能强力驱动
Strongly Powered by AbleSci AI