Engineering Papers⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3031186

Enhancing Cluster Identification in Atom Probe Tomography Data Using Transfer Learning

Tang, Yalei [Idaho National Laboratory]·Bachhav, Mukesh [Idaho National Laboratory] (ORCID:0000000181046032)
View original source ↗Read source document ↗Export metadata ↓

Abstract

Atom probe tomography (APT) has enabled the direct visualization of solute clusters, providing valuable insights into material structures. This clustering is crucial for understanding the nanoscale composition and behavior of materials, which can significantly influence their mechanical and physical properties. However, the widely used clustering methods in the APT community face challenges such as subjective parametric selection and limited applicability, particularly in dealing with overlapping clusters, nested clusters, and artifacts across different scales, such as precipitates and dislocations. To address these challenges, we present a framework based on density-based cluster analysis that aims to be less dependent on user input, reproducible, and robust.

Explore related subjects

Density-based clusteringHDBSCANTransfer learning36 - MATERIALS SCIENCEAtom probe tomography

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Tang, Yalei [Idaho National Laboratory], Bachhav, Mukesh [Idaho National Laboratory] (ORCID:0000000181046032). 2025-06-02. Enhancing Cluster Identification in Atom Probe Tomography Data Using Transfer Learning. https://www.osti.gov/biblio/3031186

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2025

Enhancing Cluster Identification in Atom Probe Tomography Data Using Transfer Learning

Atom Probe Tomography (APT) is a powerful technique for visualizing the atomic-scale distribution of solutes in materials, but quantitative cluster analysis of APT datasets remains a challenge due to the need for subjective parameter selection in clustering algorithms. While distance-based and density-based methods such as HDBSCAN are widely used, their performance is highly sensitive to user-defined parameters, which undermines reproducibility and accuracy. This study proposes an image-based, deep learning-aided workflow for automating parameter selection and cluster detection in APT data analysis. By projecting 3D APT point clouds onto 2D planes, we leverage pretrained convolutional neural networks (ConvNeXt-Tiny and ResNet-50) through transfer learning to predict the number of clusters present in synthetic datasets. The output is used to guide K-means clustering and estimate HDBSCAN parameters, specifically minimum cluster size and minimum sample points. This approach reduces reliance on manual parameter tuning, improving consistency and scalability. The methodology demonstrates the feasibility of using image-based deep learning for interpreting complex spatial patterns in APT data, enabling faster and more objective analysis. The complete workflow and code are made publicly available to support reproducibility and future research.

Density-based clustering↗