论文标题
使用卷积神经网络和Strehl比率选择最佳的茎收敛角度选择
Optimal STEM Convergence Angle Selection using a Convolutional Neural Network and the Strehl Ratio
论文作者
论文摘要
选择正确的收敛角对于在扫描透射电子显微镜（STEM）中获得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（Rayleigh）的四分之一相规则，以评估测量像差功能的探测质量和不确定性导致收敛角和较低分辨率的选择。在这里，我们表明StreHL比例提供了准确和有效的计算标准，以评估STEM的探针大小。通过模拟数据集选择从单个电子ronchigram选择收敛角度，在Strehl比率上训练的卷积神经网络表现出优于经验丰富的显微镜。该网络生成数万个模拟的Ronchigram示例，以选择收敛角，平均以毫秒速度（0.02％的人类评估时间）提供探针，平均达到85％，达到最佳尺寸。对实验性的Ronchigrams进行的定性评估有意引入畸变，这表明最佳收敛角度大小的趋势是很好的建模，但准确性很高，需要广泛的训练数据集。使用Strehl比率和机器学习对Ronchigram的这种即时评估突出了一个可行的途径，通往像差校正的电子显微镜的快速，自动对齐。
Selection of the correct convergence angle is essential for achieving the highest resolution imaging in scanning transmission electron microscopy (STEM). Use of poor heuristics, such as Rayleigh's quarter-phase rule, to assess probe quality and uncertainties in measurement of the aberration function result in incorrect selection of convergence angles and lower resolution. Here, we show that the Strehl ratio provides an accurate and efficient to calculate criteria for evaluating 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% 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 extensive training datasets. This near immediate assessment of Ronchigrams using the Strehl ratio and machine learning highlights a viable path toward rapid, automated alignment of aberration-corrected electron microscopes.
