Neural network approximation of tip-abrasion effects in AFM imaging

Abstract

The abrasion (wear) of tips used in scanning force microscopy (SFM) directly influences SFM image quality and is therefore of great relevance to quantitative SFM measurements. The increasing implementation of automated SFM measurement schemes has become a strong driving force for increasing efforts towards the prediction of tip wear, as it needs to be ensured that the probe is exchanged before a level of tip wear is reached that adversely affects the measurement quality. In this paper, we describe the identification of tip abrasion in a system of SFM measurements. We attempt to model the tip-abrasion process as a concatenation of a mapping from the measured AFM data to a regression vector and a nonlinear mapping from the regressor space to the output space. The mapping is formed as a basis function expansion. Feedforward neural networks are used to approximate this mapping. The one-hidden layer network gave a good quality of fit for the training and test sets for the tip-abrasion system. We illustrate our method with AFM measurements of both fine periodic structures and randomly oriented sharp features and compare our neural network results with those obtained using other methods.

Grain and Grain Boundary Conduction Channels in Copper Iodide Thin Films

“…For each sequence of scans, new as-received probes are utilized to avoid the problem of abrasion at the tip of the apex of the cone. [23][24][25][26] All measurements were conducted at a constant temperature between 18 and 22 °C as well as at a humidity between 30% and 40% to minimize the influence of varying ambient conditions on the measured current. [27] Within a measurement sequence, the variation is rather AE1 °C and AE5% humidity.…”

Geometric Back-Propagation in Morphological Neural Networks

“…Probe or material abrasion is a challenging issue in obtaining high-quality scans [37,38,40,41,43] in AFM. In Table 1, in the sixth and ninth column it is shown that Probe Learning by bounding recovers the best reconstruction R. Besides surface predictions, the geometric properties of the probe are learned by the morphological layer.…”

Geometric Back-Propagation in Morphological Neural Networks

“…As a consequence, the quality of the probe geometry has to be monitored constantly. Estimating probe and surface abrasion is ill-defined because it may happen to either or both structures [37]: the image signal results from both the probe and the surface. Examples of estimating abrasion effects in literature are: [38] studies imaging artefacts in AFM data, and corrects for common distortions using basic image statistics.…”

“…loss of probe convexity-such that automated conditioning of probe geometry can take place; [41] extends this idea to work for general impurities and corrupted imagery. They employ a VGG to automatically classify whether probe quality in measurements is acceptable or not; later work [42] also enables probe classification on partial scans; in [43] a CNN is tasked with classifying the quality of the measurements in a life system; [37] uses neural networks to model the change in probe geometry during scanning; [44] uses a U-net [45] to reconstruct surfaces from synthetic data.…”