Reducing molecular simulation time for AFM images based on super-resolution methods

[摘要] Atomic force microscopy (AFM) has been an important tool for nanoscale imaging and characterization with atomic and subatomicresolution. Theoretical investigations are getting highly important for the interpretation of AFM images. Researchers have used molecular simulation to examine the AFM imaging mechanism. With a recent flurry of researches applying machine learning to AFM,AFM images obtained from molecular simulation have also been used as training data. However, the simulation is incredibly timeconsuming. In this paper, we apply super-resolution methods, including compressed sensing and deep learning methods, to reconstruct simulated images and to reduce simulation time. Several molecular simulation energy maps under different conditions arepresented to demonstrate the performance of reconstruction algorithms. Through the analysis of reconstructed results, we find thatboth presented algorithms could complete the reconstruction with good quality and greatly reduce simulation time. Moreover, thesuper-resolution methods can be used to speed up the generation of training data and vary simulation resolution for AFM machinelearning.

[学科分类] 环境监测和分析

[关键词] atomic force microscopy;Bayesian compressed sensing;convolutional neural network;molecular dynamics simulation;superresolution