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

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.

Computer Vision-aided Atom Tracking in STEM Imaging

To address the SMC'17 data challenge -- "Data mining atomically resolved images for material properties", we first used the classic "blob detection" algorithms developed in computer vision to identify all atom centers in each STEM image frame. With the help of nearest neighbor analysis, we then found and labeled every atom center common to all the STEM frames and tracked their movements through the given time interval for both Molybdenum or Selenium atoms.

Discovering Features in Sr$_{14}$Cu$_{24}$O$_{41}$ Neutron Single Crystal Diffraction Data by Cluster Analysis

To address the SMC'18 data challenge, "Discovering Features in Sr$_{14}$Cu$_{24}$O$_{41}$", we have used the clustering algorithm "DBSCAN" to separate the diffuse scattering features from the Bragg peaks, which takes into account both spatial and photometric information in the dataset during in the clustering process. We find that, in additional to highly localized Bragg peaks, there exists broad diffuse scattering patterns consisting of distinguishable geometries. Besides these two distinctive features, we also identify a third distinguishable feature submerged in the low signal-to-noise region in the reciprocal space, whose origin remains an open question.