A deep-reinforcement-learning agent that dynamically tunes PI control gains reduced deflection errors by 26% to 90% on commercial scanning probe microscope scans.
General Resolution Enhancement Method in Atomic Force Microscopy (AFM) Using Deep Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper develops a resolution enhancement method for post-processing the images from Atomic Force Microscopy (AFM). This method is based on deep learning neural networks in the AFM topography measurements. In this study, a very deep convolution neural network is developed to derive the high-resolution topography image from the low-resolution topography image. The AFM measured images from various materials are tested in this study. The derived high-resolution AFM images are comparable with the experimental measured high-resolution images measured at the same locations. The results suggest that this method can be developed as a general post-processing method for AFM image analysis.
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PICTS: A Novel Deep Reinforcement Learning Approach for Dynamic P-I Control in Scanning Probe Microscopy
A deep-reinforcement-learning agent that dynamically tunes PI control gains reduced deflection errors by 26% to 90% on commercial scanning probe microscope scans.