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 108–1010 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.
KeywordsScientific visualization Feature extraction Unsupervised learning and clustering Volumetric dataset
We first thank Dr. Hassina Z. Bilheux (Neutron Scattering Division, ORNL) for providing the Turbine dataset used in this article, and Dr. Jean-Christophe Bilheux (Neutron Scattering Division, ORNL) for discussions and illustrations of functionalities of tomography visualization in VGStudio. We also thank our colleagues, Mr. Eric Lingerfelt (EarthCube Science Support Office, UCAR) and Dr. Christina Hoffmann (Neutron Scattering Division, ORNL) for insightful discussions. This research used resources of the Oak Ridge Leadership Computing Facility (OLCF) and the Compute and Data Environment for Science (CADES) at ORNL, which are supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. Research conducted at ORNL’s Spallation Neutron Source and the High Flux Isotope Reactor was sponsored by the Scientific User Facilities Division, Office of Basic Energy Sciences, U.S. Department of Energy.
- 1.Kreylos, O., Weber, G.H., Bethel, E.W., Shalf, J.M., Hamann, B., Joy, K.I.: Remote interactive direct volume rendering of AMR Data. Technical report, LBNL 49954, Lawrence Berkeley National Laboratory (2002)Google Scholar
- 2.Watkins, T.R., Bilheux, H.Z., An, K., Payzant, E.A., Dehoff, R.R., Duty, C.E., Peter, W.H., Blue, C.A., Brice, C.A.: Neutron characterization for additive manufacturing. Adv. Mater. Process. 171(3), 23–27 (2013)Google Scholar
- 6.Ester, M., Kriegel, H.-P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters a density-based algorithm for discovering clusters in large spatial databases with noise. In: Simoudis, E., Han, J., Fayyad, U. (eds.) The Second International Conference on Knowledge Discovery and Data Mining (KDD 1996), pp. 226–231. AAAI Press (1996)Google Scholar
- 7.Piper, D., Schiecke, K., Witte, H., Leistritz, L.: Comparative study of methods for solving the correspondence problem in EMD applications. Curr. Dir. Biomed. Eng. 2(1), 225–228 (2016)Google Scholar
- 8.Gault, B., Moody, M.P., Cairney, J.M., Ringer, S.P.: Atom Probe Microscopy, Chapt 8. In: Springer Series in Materials Science, vol. 160, p. 261. Springer (2012)Google Scholar
- 13.Lingerfelt, E.J., Belianinov, A., Endeve, E., Ovchinnikov, O., Somnath, S., Borreguero, J.M., Grodowitz, N., Park, B., Archibald, R.K., Symons, C.T., Kalinin, S.V., Messer, O.E.B., Shankar, M., Jesse, S.: BEAM: a computational workflow system for managing and modeling material characterization data in HPC environments. In: International Conference on Computational Science 2016, Procedia Computer Science, vol. 80, pp. 2276–2280 (2016)CrossRefGoogle Scholar