Classification of Reflection High-Energy Electron Diffraction Pattern Using Machine Learning

Kwoen, Jinkwan; Arakawa, Yasuhiko

doi:10.1021/acs.cgd.0c00506

Cited by 21 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…反射高能电子衍射(RHEED)可现场观察分子束外延生长过程中的样品表面行为, 具有广泛的应用前景, 但 RHEED 模式分析对操作人员具有较高要求, 需要其拥有大量的专业知识积累和操作经验。因此，将其应用于实时反馈控制是十分困难的. Kwoen 团队 [50] 使用卷积神经网络(CNN)的机器学习方法识别输入数据库中的特征点, 其适用于具有可变性的图像分类. Kwoen 团队提出了一种在连续旋转过程中识别 GaAs 衬底的 RHEED 模式测量方法, 并建立了生长条件的数据集.…”

Section: 辅助表征unclassified

Recent Advance of Machine Learning in Selecting New Materials

Qi¹,

Hu²,

Wang³

et al. 2023

Acta Chimica Sinica

View full text Add to dashboard Cite

The new material industry is the foundation of technological change in many related fields, and also the forerunner of the development of new energy, aerospace, electronic information and other high-tech industries. Traditional means cannot meet the development needs of modern society because of disadvantages such as high cost, low efficiency and long commercial cycle. In recent years, with the application of big data combined with artificial intelligence in a deeper degree, data-driven machine learning has made great progress in the design, screening and performance prediction of new materials, which has greatly promoted the development and application of new materials. In this review, the basic process of machine learning, the algorithms commonly used in materials science and the relevant materials database are summarized. This review focuses on the application of machine learning in different functions, as well as the performance prediction in the fields of catalyst materials, lithium-ion batteries, semiconductor materials and alloy materials, presenting the latest progress in materials development. Finally, machine learning in the application of new materials are analyzed and prospected.

show abstract

Section: 辅助表征unclassified

Recent Advance of Machine Learning in Selecting New Materials

Qi¹,

Hu²,

Wang³

et al. 2023

Acta Chimica Sinica

View full text Add to dashboard Cite

show abstract

“…306 CNNs have been also used for Bragg peak integration of neutron crystallographic images with the algorithm being capable of recognizing both location and shape of the peaks in the input image. 307 Besides, CNNs can be used for similar purposes in classifying crystallographic images from reflection high-energy electron diffraction 308 and X-ray freeelectron laser. 77 Furthermore, serial crystallography would greatly profit from the real-time classification of images with and without a diffraction pattern provided by CNNs.…”

Section: High Throughput Materials Discovery and Crystal Characteriza...mentioning

confidence: 99%

Applications of Artificial Intelligence and Machine Learning Algorithms to Crystallization

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence and specifically machine learning applications are nowadays used in a variety of scientific applications and cutting-edge technologies, where they have a transformative impact. Such an assembly of statistical and linear algebra methods making use of large data sets is becoming more and more integrated into chemistry and crystallization research workflows. This review aims to present, for the first time, a holistic overview of machine learning and cheminformatics applications as a novel, powerful means to accelerate the discovery of new crystal structures, predict key properties of organic crystalline materials, simulate, understand, and control the dynamics of complex crystallization process systems, as well as contribute to high throughput automation of chemical process development involving crystalline materials. We critically review the advances in these new, rapidly emerging research areas, raising awareness in issues such as the bridging of machine learning models with first-principles mechanistic models, data set size, structure, and quality, as well as the selection of appropriate descriptors. At the same time, we propose future research at the interface of applied mathematics, chemistry, and crystallography. Overall, this review aims to increase the adoption of such methods and tools by chemists and scientists across industry and academia.

show abstract

“…With the development of artificial intelligence technology, one should consider adopting machine learning (ML) methods for analyzing the complete RHEED data to advance the existing thin-film growth methods and design fully autonomous material synthesis techniques [ 13 – 16 ]. Deep learning models, such as convolutional neural networks, classified the surface pattern and reconstruction of GaAs [ 17 ] and Fe x O y [ 18 ] with a high accuracy based on the RHEED data. The surface evolution and transitions in an entire RHEED data sequence were also examined for various oxide materials using unsupervised ML methods such as principal component analysis (PCA) and K-means clustering [ 19 – 21 ].…”

Section: Introductionmentioning

confidence: 99%

Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth

et al. 2023

View full text Add to dashboard Cite

In situ reflective high-energy electron diffraction (RHEED) is widely used to monitor the surface crystalline state during thin-film growth by molecular beam epitaxy (MBE) and pulsed laser deposition. With the recent development of machine learning (ML), ML-assisted analysis of RHEED videos aids in interpreting the complete RHEED data of oxide thin films. The quantitative analysis of RHEED data allows us to characterize and categorize the growth modes step by step, and extract hidden knowledge of the epitaxial film growth process. In this study, we employed the ML-assisted RHEED analysis method to investigate the growth of 2D thin films of transition metal dichalcogenides (ReSe2) on graphene substrates by MBE. Principal component analysis (PCA) and K-means clustering were used to separate statistically important patterns and visualize the trend of pattern evolution without any notable loss of information. Using the modified PCA, we could monitor the diffraction intensity of solely the ReSe2 layers by filtering out the substrate contribution. These findings demonstrate that ML analysis can be successfully employed to examine and understand the film-growth dynamics of 2D materials. Further, the ML-based method can pave the way for the development of advanced real-time monitoring and autonomous material synthesis techniques. Graphical Abstract

show abstract

Classification of Reflection High-Energy Electron Diffraction Pattern Using Machine Learning

Cited by 21 publications

References 23 publications

Recent Advance of Machine Learning in Selecting New Materials

Recent Advance of Machine Learning in Selecting New Materials

Applications of Artificial Intelligence and Machine Learning Algorithms to Crystallization

Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth

Contact Info

Product

Resources

About