发表机构
Bredesen Center for Interdisciplinary Research, University of Tennessee; University of Tennessee; Center for Advanced Materials and Manufacturing, University of Tennessee; Hunter College, City University of New York; University of Tennessee-Oak Ridge Innovation Institute, University of Tennessee（田纳西大学布雷德森跨学科研究中心; 田纳西大学; 田纳西大学先进材料与制造中心; 纽约市立大学亨特学院; 田纳西大学-橡树岭创新研究院，田纳西大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究开发了一个基于物理的数字仿真工具包，通过模拟噪声生成大量真实STM图像，用于训练有监督去噪模型，在Cu(111)表面图像上优于无监督方法，促进科学发现。
AI 中文摘要
扫描隧道显微镜（STM）是一种广泛用于在原子尺度表征材料表面的工具，在凝聚态物理和材料科学的诸多发现中发挥着关键作用。尽管其具有极高的空间分辨率，STM 却是最敏感的显微技术之一，极易受到噪声影响。现有的无监督去噪方法训练成本非常低，但这些方法主要侧重于去除噪声，对关键物理信息的恢复能力有限。虽然有监督方法可以提供更优越的性能，但主要瓶颈在于需要大量成对的干净-含噪实验图像，而这些图像难以实际获取。因此，我们开发了一个低成本的物理驱动数字工具包，以快速生成大量真实的 STM 图像。首先，我们从选定的材料系统模拟干净图像。然后，基于对 STM 实验中存在的伪影和噪声的物理特性的先验知识，我们构建了多种伪影-噪声函数，如高斯电子噪声、1/f 闪烁噪声、扫描线噪声、背景倾斜和机械漂移。这些基于物理的噪声成分随后被添加到模拟的干净图像中，以生成真实的 STM 图像。我们展示了所提出的数字工具包能够生成适用于 AI 的数据，用于对铜和铅的（111）表面图像进行去噪，同时保留原子、缺陷和电子波。我们还验证了从 Cu(111) 图像中学习由量子干涉引起的电子波模式的下游图像分析质量。结果表明，在数字生成的 AI-ready 数据上训练的有监督模型，比基准的无监督方法更能有效地对 Cu(111) 图像进行去噪并学习电子波模式，这表明所提出的工具包有助于科学发现。
英文摘要
Scanning Tunneling Microscopy (STM) is a widely used tool for characterizing surfaces of materials at the atomic scale, playing a crucial role in discoveries across condensed matter physics and materials science. Despite its extreme spatial resolution, STM is one of the most sensitive microscopy techniques and is highly prone to noise. While existing unsupervised denoising methods are very cheap to train, these are primarily focused on removing the noise with minimal recovery of key physical information. While supervised methods can offer superior performance, the major bottleneck is that a large amount of paired clean-noisy experimental images is required which are impractical to obtain. Thus, we developed a low-cost physics-driven digital toolkit to rapidly generate large volume of realistic STM images. Firstly, we simulate clean images from a chosen material system. Then, with prior knowledge of the physical characteristics of the artifacts and noise present in STM experiments, we formulate several artifact-noise functions such as Gaussian electronic noise, 1/f flicker noise, scan-line noise, background tilt and mechanical drift. These physically informed noise components are then added to the simulated clean images to generate realistic STM images. We demonstrated the capability of the proposed digital toolkit to generate AI-ready data for denoising images of the (111) surfaces of copper and lead, while preserving atoms, defects, and electron waves. We also validated the quality of the downstream image analysis of learning electron wave patterns induced by quantum interference from Cu(111) images. Results show that the supervised models trained on digitally generated AI-ready data can more effectively denoise and learn electron wave patterns on Cu(111) images than benchmarked unsupervised approaches, indicating that the proposed toolkit facilitate scientific discovery.
Comments17 pages, 6 figures in main text and 2 supplementary figures
