Applied machine learning for atom probe tomography

Thumbnail Image

Files

master_Wu_Hao_2022.pdf (14.24 MB)

URL

Journal Title

Journal ISSN

Volume Title

Sähkötekniikan korkeakoulu | Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.

Authors

Date

2022-12-16

Department

Major/Subject

Control, Robotics and Autonomous Systems

Mcode

ELEC3025

Degree programme

AEE - Master’s Programme in Automation and Electrical Engineering (TS2013)

Language

en

Pages

38+9

Series

Abstract

Atom Probe Tomography (APT) is a significant method in exploring the crystal structure. Former work in APT focuses on detecting the crystal based on physics principles. This paper raises a new data-based method for the reconstruction of sample crystal structure, implementing machine learning (ML) models with the detector information as input. First, a simulation for field evaporation process in APT is provided. Next, various ML models are built to obtain the 3D reconstructed atoms distribution image. The discussion of ML models' performance is provided.

Description

Supervisor

Alava, Mikko

Thesis advisor

Lomakin, Ivan

Keywords

machine learning, atom probe tomography, Bayesian method, artificial neural network, reconstruction

Other note

Citation

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202212257341

Collections

[dipl] Sähkötekniikan korkeakoulu / ELEC