Optimal STEM Convergence Angle Selection Using a Convolutional Neural Network and the Strehl Ratio,Microscopy and Microanalysis

当前位置： X-MOL 学术 › Microsc. Microanal. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Optimal STEM Convergence Angle Selection Using a Convolutional Neural Network and the Strehl Ratio
Microscopy and Microanalysis ( IF 2.9 ) Pub Date : 2020-08-06 , DOI: 10.1017/s1431927620001841
Noah Schnitzer _{1,

2} , Suk Hyun Sung ₁ , Robert Hovden _{1,

3}

Affiliation

The selection of the correct convergence angle is essential for achieving the highest resolution imaging in scanning transmission electron microscopy (STEM). The use of poor heuristics, such as Rayleigh's quarter-phase rule, to assess probe quality and uncertainties in the measurement of the aberration function results in the incorrect selection of convergence angles and lower resolution. Here, we show that the Strehl ratio provides an accurate and efficient way to calculate criteria for evaluating the probe size for STEM. A convolutional neural network trained on the Strehl ratio is shown to outperform experienced microscopists at selecting a convergence angle from a single electron Ronchigram using simulated datasets. Generating tens of thousands of simulated Ronchigram examples, the network is trained to select convergence angles yielding probes on average 85% nearer to optimal size at millisecond speeds (0.02% of human assessment time). Qualitative assessment on experimental Ronchigrams with intentionally introduced aberrations suggests that trends in the optimal convergence angle size are well modeled but high accuracy requires a high number of training datasets. This near-immediate assessment of Ronchigrams using the Strehl ratio and machine learning highlights a viable path toward the rapid, automated alignment of aberration-corrected electron microscopes.

中文翻译：

使用卷积神经网络和 Strehl 比的最佳 STEM 会聚角选择

选择正确的会聚角对于在扫描透射电子显微镜 (STEM) 中实现最高分辨率成像至关重要。使用较差的启发式方法（例如瑞利四分之一相位规则）来评估像差函数测量中的探头质量和不确定性会导致会聚角选择不正确和分辨率降低。在这里，我们展示了 Strehl 比率提供了一种准确有效的方法来计算评估 STEM 探针尺寸的标准。在 Strehl 比率上训练的卷积神经网络在使用模拟数据集从单电子 Ronchigram 选择会聚角方面表现优于经验丰富的显微镜专家。生成数以万计的模拟 Ronchigram 示例，该网络经过训练以选择收敛角，以毫秒的速度（人类评估时间的 0.02%）产生平均接近最佳尺寸 85% 的探针。对有意引入像差的实验性 Ronchigram 的定性评估表明，最佳会聚角大小的趋势得到了很好的建模，但高精度需要大量的训练数据集。这种使用 Strehl 比率和机器学习对 Ronchigrams 进行的近乎即时的评估突出了一条通往像差校正电子显微镜快速、自动对齐的可行途径。对有意引入像差的实验性 Ronchigram 的定性评估表明，最佳会聚角大小的趋势得到了很好的建模，但高精度需要大量的训练数据集。这种使用 Strehl 比率和机器学习对 Ronchigrams 进行的近乎即时的评估突出了一条通往像差校正电子显微镜快速、自动对齐的可行途径。对有意引入像差的实验性 Ronchigram 的定性评估表明，最佳会聚角大小的趋势得到了很好的建模，但高精度需要大量的训练数据集。这种使用 Strehl 比率和机器学习对 Ronchigrams 进行的近乎即时的评估突出了一条通往像差校正电子显微镜快速、自动对齐的可行途径。

更新日期：2020-08-06

点击分享查看原文

点击收藏

公开下载

阅读更多本刊最新论文本刊介绍/投稿指南11