STM Image Analysis using Autoencoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Binev, Peter, Moorehead, Joshua, Parambath, Ayush, Parrella, Luke, Pumphrey, Rori, Savu, Miruna
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910795394187264
author Binev, Peter
Moorehead, Joshua
Parambath, Ayush
Parrella, Luke
Pumphrey, Rori
Savu, Miruna
author_facet Binev, Peter
Moorehead, Joshua
Parambath, Ayush
Parrella, Luke
Pumphrey, Rori
Savu, Miruna
contents This study explores the application of Convolutional Autoencoders (CAEs) for analyzing and reconstructing Scanning Tunneling Microscopy (STM) images of various crystalline lattice structures. We developed two distinct CAE architectures to process simulated STM images of simple cubic, body-centered cubic (BCC), face-centered cubic (FCC), and hexagonal lattices. Our models were trained on $17\times17$ pixel patches extracted from $256\times256$ simulated STM images, incorporating realistic noise characteristics. We evaluated the models' performance using Mean Squared Error (MSE) and Structural Similarity (SSIM) index, and analyzed the learned latent space representations. The results demonstrate the potential of deep learning techniques in STM image analysis, while also highlighting challenges in latent space interpretability and full image reconstruction. This work lays the foundation for future advancements in automated analysis of atomic-scale imaging data, with potential applications in materials science and nanotechnology.
format Preprint
id arxiv_https___arxiv_org_abs_2501_13283
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STM Image Analysis using Autoencoders
Binev, Peter
Moorehead, Joshua
Parambath, Ayush
Parrella, Luke
Pumphrey, Rori
Savu, Miruna
Numerical Analysis
65D40, 68T07
G.1.10
This study explores the application of Convolutional Autoencoders (CAEs) for analyzing and reconstructing Scanning Tunneling Microscopy (STM) images of various crystalline lattice structures. We developed two distinct CAE architectures to process simulated STM images of simple cubic, body-centered cubic (BCC), face-centered cubic (FCC), and hexagonal lattices. Our models were trained on $17\times17$ pixel patches extracted from $256\times256$ simulated STM images, incorporating realistic noise characteristics. We evaluated the models' performance using Mean Squared Error (MSE) and Structural Similarity (SSIM) index, and analyzed the learned latent space representations. The results demonstrate the potential of deep learning techniques in STM image analysis, while also highlighting challenges in latent space interpretability and full image reconstruction. This work lays the foundation for future advancements in automated analysis of atomic-scale imaging data, with potential applications in materials science and nanotechnology.
title STM Image Analysis using Autoencoders
topic Numerical Analysis
65D40, 68T07
G.1.10
url https://arxiv.org/abs/2501.13283