Here, a resolution enhancement method is developed for post-processing 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 a high-resolution topography image from a 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.Atomic force microscopy (AFM) is a well-known powerful technique to image the surface structures and properties at nanoscale [1,2] with ultrahigh resolution. It tracks cantilever motion affected by the interaction between the tip and the sample surface; therefore, the resolution can reach the atomic or molecular level. [3][4][5] However, the unavoidable experimental errors, such as "tip crash," [6] the cross-talk between topographic and electrostatic information, [7] the large height variation of the sample surface, [8] and the influence by the properties of the sample or the ambient environment [9] can severely reduce the spatial resolution of the AFM images. In addition, scanning a large area with high resolution usually needs long time and may cause the drift of the image and tip wearing as well as the distortion of the nanostructures on the sample surface. [10] Generally speaking, low-resolution images certainly contain insufficient information, which may cause some of the important features, including grain boundary, surface defect, dislocation and interface unclear or even ignored. Hence, several methods and techniques were proposed to enhance the resolution and quality of the AFM images, such as by improving the shape and properties of the tip or cantilever, [11][12][13][14] the development and application of the multiple frequency excitation techniques, [15][16][17][18] the contour metrology, [19]