Volumetric Data Exploration with Machine Learning-Aided Visualization in Neutron Science

TL;DR

This paper presents a machine learning-based method using DBSCAN for efficient analysis and visualization of large volumetric neutron scattering datasets, improving feature detection and de-noising in 3D visualization.

Contribution

It introduces a novel application of unsupervised machine learning, specifically DBSCAN, for volumetric data analysis and visualization in neutron science, handling extremely large datasets.

Findings

DBSCAN effectively denoises data and detects features.

Using intensity as a weighting factor enhances clustering accuracy.

Method improves visualization of internal structures in neutron data.

Abstract

Recent advancements in neutron and X-ray sources, instrumentation and data collection modes have significantly increased the experimental data size (which could easily contain 10$^{8}$ -- 10$^{10}$ data points), so that conventional volumetric visualization approaches become inefficient for both still imaging and interactive OpenGL rendition in a 3D setting. We introduce a new approach based on the unsupervised machine learning algorithm, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), to efficiently analyze and visualize large volumetric datasets. Here we present two examples of analyzing and visualizing datasets from the diffuse scattering experiment of a single crystal sample and the tomographic reconstruction of a neutron scanning of a turbine blade. We found that by using the intensity as the weighting factor in the clustering process, DBSCAN becomes very effective in de-noising and feature/boundary detection, and thus enables better visualization of the hierarchical internal structures of the neutron scattering data.