Volumetric Data Exploration with Machine Learning-Aided Visualization in Neutron Science
Preprint
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 $10^{8}$-$10^{10}$ points), so that conventional volumetric visualization approaches become inefficient for both still imaging and interactive OpenGL rendition in a 3-D 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, including a single crystal diffuse scattering dataset and a neutron tomography dataset. We found that by using the intensity as the weight factor during clustering, the algorithm becomes very effective in de-noising and feature/boundary detection, and thus enables better visualization of the hierarchical internal structures of the scattering data.
Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Comparative study of methods for solving the correspondence problem in EMD applicationsCurrent Directions in Biomedical Engineering, 2016
- State of the Art in Transfer Functions for Direct Volume RenderingComputer Graphics Forum, 2016
- Expanding Lorentz and spectrum corrections to large volumes of reciprocal space for single-crystal time-of-flight neutron diffractionJournal of Applied Crystallography, 2016
- BEAM: A Computational Workflow System for Managing and Modeling Material Characterization Data in HPC EnvironmentsProcedia Computer Science, 2016
- Mantid—Data analysis and visualization package for neutron scattering and SR experimentsNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2014
- The physics of volume renderingEuropean Journal of Physics, 2014
- Muon tomography imaging algorithms for nuclear threat detection inside large volume containers with the Muon Portal detectorNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2013
- A density-based segmentation for 3D images, an application for X-ray micro-tomographyAnalytica Chimica Acta, 2012
- Atom Probe Microscopy2012
- Volume Visualization: A Technical Overview with a Focus on Medical ApplicationsJournal of Digital Imaging, 2010