ML-APT is a machine learning framework specifically designed to identify and quantify Ordered Interstitial Complexes (OICs) in medium-entropy alloys. Leveraging advanced in-situ air-doped additive manufacturing, this project integrates Atom Probe Tomography (APT) with machine learning algorithms to achieve high-precision identification and quantitative analysis of nanoscale short-range order (SRO) structures and interstitial complexes.

Read full text Summarise with VIRAT
Authors: Jiawei Yin
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

ML-APT: Machine Learning-enhanced Atom Probe Tomography FrameworkProject OverviewML-APT is a machine learning framework specifically designed to identify and quantify Ordered Interstitial Complexes (OICs) in medium-entropy alloys. Leveraging advanced in-situ air-doped additive manufacturing, this project integrates Atom Probe Tomography (APT) with machine learning algorithms to achieve high-precision identification and quantitative analysis of nanoscale short-range order (SRO) structures and interstitial complexes.

Fields of Study & Subjects

Advanced Materials Characterization Techniques Machine Learning in Materials Science High Entropy Alloys Studies

Publication details

Journal / source
Figshare
Publication date
30 March 2026
Language
EN
Document type
Dataset