Scanning tunneling state recognition with multi-class neural network ensembles
Scanning tunneling state recognition with multi-class neural network ensembles
复制标题
DOI：
10.1063/1.5099590
复制
发表时间：
2019-10-01
影响因子：
1.6
通讯作者：
Swart, I.
中科院分区：
文献类型：
--
作者：
Gordon, O.;D'Hondt, P.;Swart, I.
扫描探针显微镜面临的最大障碍之一是不断需要在原位校正扫描探针中的缺陷。目前这是一个耗时的人工过程，自动化将大大受益。在这里，我们介绍了一种卷积神经网络协议，该协议能够自动识别金属和非金属表面上各种理想和不理想的扫描隧道尖端状态。通过将表现最好的模型组合成多数投票系综，我们发现可以以0.89的平均精度和0.95的平均接收者操作者特征曲线面积区分H：Si（100）的期望状态。更一般地，高质量和低质量的尖端可以以0.96的平均精度和0.98的接近完美的曲线下面积来区分。通过微小的修改，我们还成功地自动识别了Au（111）和Cu（111）表面上的不期望的非表面特异性状态。在这些情况下，我们发现平均精密度分别为0.95和0.75，曲线下面积分别为0.98和0.94。如果训练数据是可用的，这些合奏，因此，使完全自主的扫描隧道状态识别范围广泛的典型扫描条件。(C)2019年作者。
One of the largest obstacles facing scanning probe microscopy is the constant need to correct flaws in the scanning probe in situ. This is currently a manual, time-consuming process that would benefit greatly from automation. Here, we introduce a convolutional neural network protocol that enables automated recognition of a variety of desirable and undesirable scanning tunneling tip states on both metal and nonmetal surfaces. By combining the best performing models into majority voting ensembles, we find that the desirable states of H:Si(100) can be distinguished with a mean precision of 0.89 and an average receiver-operator-characteristic curve area of 0.95. More generally, high and low-quality tips can be distinguished with a mean precision of 0.96 and near perfect area-under-curve of 0.98. With trivial modifications, we also successfully automatically identify undesirable, non-surface-specific states on surfaces of Au(111) and Cu(111). In these cases, we find mean precisions of 0.95 and 0.75 and area-under-curves of 0.98 and 0.94, respectively. Provided that training data are available, these ensembles therefore enable fully autonomous scanning tunneling state recognition for a wide range of typical scanning conditions. (C) 2019 Author(s).