Pavel Potocek, Cigdem Ozsoy-Keskinbora, Philipp Müller, Thorsten Wieczorek, Maurice Peemen, Philipp Slusallek, Bert Freitag
{"title":"Artificial Intelligence-Driven Smart Scan: A Rapid, Automatic Approach for Comprehensive Imaging and Spectroscopy for Fast Compositional Analysis","authors":"Pavel Potocek, Cigdem Ozsoy-Keskinbora, Philipp Müller, Thorsten Wieczorek, Maurice Peemen, Philipp Slusallek, Bert Freitag","doi":"10.1002/aisy.202300745","DOIUrl":null,"url":null,"abstract":"<p>Nanomaterial properties and functionalities are influenced by their shape, size, and chemical composition. The importance of these parameters highlights the need for a statistically robust analysis of a large particle population, necessitating automation. This study introduces a neural network-empowered smart scan technique that achieves a relative increase in speed compared to traditional energy-dispersive X-ray spectroscopy (EDX) mapping. The main advantage is that it reduces the required dose, decreasing potential damage to the sample by avoiding unnecessary exposure. It holds potential use in other multimodal scanning transmission electron microscopy or scanning-based imaging approaches. In the first example, identifying particles in a matrix with a trained neural network reduces the acquisition time by two orders of magnitude. This acceleration enables a statistical compositional analysis of thousands of particles in less than 1 h. Similar improvements are observed for atomic resolution. The discrete positions of atoms identified by the trained network allow for selective EDX sampling at these centers, thereby identifying the atomic species of the column with much-reduced sampling. Consequently, a lower sampling dose is required, enabling mapping of more delicate materials with high lateral resolution and at a high statistical confidence interval. Even though manual training is still required, this approach greatly benefits repetitive quality control tasks.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8000,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300745","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/aisy.202300745","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Nanomaterial properties and functionalities are influenced by their shape, size, and chemical composition. The importance of these parameters highlights the need for a statistically robust analysis of a large particle population, necessitating automation. This study introduces a neural network-empowered smart scan technique that achieves a relative increase in speed compared to traditional energy-dispersive X-ray spectroscopy (EDX) mapping. The main advantage is that it reduces the required dose, decreasing potential damage to the sample by avoiding unnecessary exposure. It holds potential use in other multimodal scanning transmission electron microscopy or scanning-based imaging approaches. In the first example, identifying particles in a matrix with a trained neural network reduces the acquisition time by two orders of magnitude. This acceleration enables a statistical compositional analysis of thousands of particles in less than 1 h. Similar improvements are observed for atomic resolution. The discrete positions of atoms identified by the trained network allow for selective EDX sampling at these centers, thereby identifying the atomic species of the column with much-reduced sampling. Consequently, a lower sampling dose is required, enabling mapping of more delicate materials with high lateral resolution and at a high statistical confidence interval. Even though manual training is still required, this approach greatly benefits repetitive quality control tasks.
纳米材料的特性和功能受其形状、尺寸和化学成分的影响。这些参数的重要性凸显了对大量粒子群进行稳健统计分析的必要性,因此必须实现自动化。本研究介绍了一种神经网络驱动的智能扫描技术,与传统的能量色散 X 射线光谱(EDX)绘图相比,该技术的速度相对提高。其主要优点是减少了所需剂量,避免了不必要的曝光,从而降低了对样品的潜在损害。它在其他多模态扫描透射电子显微镜或基于扫描的成像方法中也有潜在用途。在第一个例子中,利用训练有素的神经网络识别矩阵中的颗粒可将采集时间缩短两个数量级。在原子分辨率方面也有类似的改进。通过训练有素的网络识别原子的离散位置,可以在这些中心进行选择性 EDX 取样,从而在大大减少取样的情况下识别柱中的原子种类。因此,所需的取样剂量更低,从而能够以高横向分辨率和高统计置信区间绘制更精细的材料。尽管仍需要人工培训,但这种方法对重复性质量控制任务大有裨益。