東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Quantitative and Efficient Scanning ...

Wei, Jingrui,

Linked to FindBook

Google Book

Amazon

博客來

Quantitative and Efficient Scanning Transmission Electron Microscopy with Machine Learning /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Quantitative and Efficient Scanning Transmission Electron Microscopy with Machine Learning // Jingrui Wei.
Author:	Wei, Jingrui,
Description:	1 electronic resource (94 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
Contained By:	Dissertations Abstracts International86-06B.
Subject:	Materials science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31767615
ISBN:	9798346874058

Quantitative and Efficient Scanning Transmission Electron Microscopy with Machine Learning /
Wei, Jingrui,

Quantitative and Efficient Scanning Transmission Electron Microscopy with Machine Learning /Jingrui Wei. - 1 electronic resource (94 pages)

Source: Dissertations Abstracts International, Volume: 86-06, Section: B.

Scanning transmission electron microscopy (STEM) has advanced the field of materials science by enabling atomic-scale structural and functional imaging. Beyond standard 2D imaging, higher dimensional data acquisition and analysis are enabling critical new sample insights. New challenges arise as well from the fast data streaming and big data volume. This thesis will discuss how advanced computational approaches and machine learning (ML) enhance the efficiency of STEM data interpretation with example topics. First, we demonstrate convolutional neural network (CNN) approaches for precise atom localization in high-resolution STEM images, establishing comprehensive benchmarks and investigating the relationship between model characteristics and performance across varying image qualities and content. Second, we introduce a deep learning-based electron counting method for ultrafast 4D-STEM detectors, utilizing a Faster-RCNN architecture to achieve accurate electron event detection at higher electron dose than previous methods. Third, a physics-informed regression model for STEM aberration measurement was developed to provide rapid aberration estimation for fine probe alignment or a starting point for sample phase reconstruction algorithms. Fourth, Z-contrast STEM imaging and 4D-STEM were used to investigate short-range order in high entropy carbides with different compositions and thermal treatment. The thesis concludes with a chapter speculating on future directions for research using ML in electron microscopy. Throughout this work, we highlight the importance of incorporating prior knowledge into the machine learning framework, ranging from data representation to model design, contributing to the broader field of quantitative electron microscopy and automation of STEM analysis.

English

ISBN: 9798346874058Subjects--Topical Terms:

543314
Materials science.
Subjects--Index Terms:

Scanning transmission electron microscopy

Quantitative and Efficient Scanning Transmission Electron Microscopy with Machine Learning /
LDR:03333nmm a22004453i 4500 001 2433044
005 20250818063916.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798346874058
035 $a (MiAaPQD)AAI31767615
035 $a AAI31767615
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Wei, Jingrui, $e author. $3 3822494
245 1 0 $a Quantitative and Efficient Scanning Transmission Electron Microscopy with Machine Learning / $c Jingrui Wei.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (94 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
500 $a Advisors: Voyles, Paul M. Committee members: Hu, Jiamian; Hu, Yu Hen; Morgan, Dane; Oh, Hyunseok.
502 $b Ph.D. $c The University of Wisconsin - Madison $d 2024.
520 $a Scanning transmission electron microscopy (STEM) has advanced the field of materials science by enabling atomic-scale structural and functional imaging. Beyond standard 2D imaging, higher dimensional data acquisition and analysis are enabling critical new sample insights. New challenges arise as well from the fast data streaming and big data volume. This thesis will discuss how advanced computational approaches and machine learning (ML) enhance the efficiency of STEM data interpretation with example topics. First, we demonstrate convolutional neural network (CNN) approaches for precise atom localization in high-resolution STEM images, establishing comprehensive benchmarks and investigating the relationship between model characteristics and performance across varying image qualities and content. Second, we introduce a deep learning-based electron counting method for ultrafast 4D-STEM detectors, utilizing a Faster-RCNN architecture to achieve accurate electron event detection at higher electron dose than previous methods. Third, a physics-informed regression model for STEM aberration measurement was developed to provide rapid aberration estimation for fine probe alignment or a starting point for sample phase reconstruction algorithms. Fourth, Z-contrast STEM imaging and 4D-STEM were used to investigate short-range order in high entropy carbides with different compositions and thermal treatment. The thesis concludes with a chapter speculating on future directions for research using ML in electron microscopy. Throughout this work, we highlight the importance of incorporating prior knowledge into the machine learning framework, ranging from data representation to model design, contributing to the broader field of quantitative electron microscopy and automation of STEM analysis.
546 $a English
590 $a School code: 0262
650 4 $a Materials science. $3 543314
650 4 $a Applied physics. $3 3343996
650 4 $a Computational physics. $3 3343998
653 $a Scanning transmission electron microscopy
653 $a Electron microscopy
653 $a Machine learning
653 $a Structure characterization
653 $a Electron dose
690 $a 0794
690 $a 0800
690 $a 0215
690 $a 0216
710 2 $a The University of Wisconsin - Madison. $b Materials Science and Engineering. $e degree granting institution. $3 3822495
720 1 $a Voyles, Paul M. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-06B.
790 $a 0262
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31767615