APS Logo

DATA: Machine Learning for High Dimentional Data: Microstructure, Images, and Fields

FOCUS · C07 · ID: 3364052

Presentations

  • Learning Shock Hydrodynamics with Generative Models

    ORAL · Invited

    –

    Publication: Jekel, C. F., Sterbentz, D. M., Stitt, T. M., Mocz, P., Rieben, R. N., White, D. A., & Belof, J. L. (2024). Machine learning visualization tool for exploring parameterized hydrodynamics. Machine Learning: Science and Technology, 5(4), 045048.

    Presenters

    • Charles F Jekel

      Lawrence Livermore National Laboratory

    Authors

    • Charles F Jekel

      Lawrence Livermore National Laboratory

    View abstract →

  • Interpreting Dynamic Compression Experiments using Machine Learning

    ORAL

    –

    Presenters

    • David Oca Montes de Oca Zapiain

      Sandia National Laboratories

    Authors

    • David Oca Montes de Oca Zapiain

      Sandia National Laboratories

    • Samantha Brozak

      Sandia National Laboratories

    • Brendan Donohoe

      Sandia National Laboratories

    • Tommy Ao

      Sandia National Laboratories

    • Mark Rodriguez

      Sandia National Laboratories

    • Marcus David Knudson

      Sandia National Laboratories

    • Nathan P Brown

      Sandia National Laboratories

    • J. Matthew D Lane

      Sandia National Laboratories

    View abstract →

  • Physics-Aware Convolutional Neural Networks for Modelling Energetic Material in the Weak Shock Regime

    ORAL

    –

    Publication: 1. P. C. Nguyen, et al., PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling, in Forty-first International Conference on Machine Learning (2024)<br>2. X. Cheng, et al., Physics-aware recurrent convolutional neural networks for modeling multiphase compressible flows. International Journal of Multiphase Flow p. 104877 (2024)<br>3. X. Cheng et al., A Physics-aware Deep Learning Model for Energetic Material Shear Band Formation in Weak Shock Regime, in preparation

    Presenters

    • Xinlun Cheng

      University of Virginia

    Authors

    • Xinlun Cheng

      University of Virginia

    • Yen t Nguyen

      University of Iowa

    • Joseph Choi

      University of Virginia

    • Pradeep Kumar Seshadri

      University of Iowa

    • Mayank Verma

      University of Iowa

    • H.S. Udaykumar

      University of Iowa

    • Stephen Baek

      University of Virginia

    View abstract →

  • Computer vision and statistical ML to analyze PBX microstructure, initiation threshold, and self-similarity in explosive hotspots

    ORAL

    –

    Publication: 1. "Topological analysis of X-ray CT data for the recognition and trending of subtle changes in microstructure under material aging," A. Maiti, A. Venkat, G. D. Kosiba, W. L. Shaw, J. D. Sain, R. K. Lindsey, C. D. Grant, P.-T. Bremer, A. G. Gyulassi, V. Pascucci, and R. H. Gee, Comput. Mat. Sci. 182, 109782 (2020).<br>2. "Effect of thermal conditioning on the initiation threshold of secondary high explosives," A. Maiti, W. L. Shaw, S. M. Clarke, C. Fox, L. A. Ke, W. N. Cheung, M. A. Burton, G. D. Kosiba, C. D. Grant, R. H. Gee, Propell. Explos. Pyrot. 49(2), e202300253 (2024).<br>3. "Image Distinguishability Analysis Testing through Principal Components and its Application to Hot Spot Scale Invariance," M. P. Kroonblawd, A. Maiti, and L. E. Fried, to be submitted (2025).<br>4. "Classifying material microstructure of accelerated aged high explosives with a computer vision approach," G. D. Kosiba, A. Maiti, R. K. Lindsey, W. L Shaw, C. D. Grant, and R. H. Gee, to be submitted (2025).

    Presenters

    • Amitesh Maiti

      Lawrence Livermore National Laboratory

    Authors

    • Amitesh Maiti

      Lawrence Livermore National Laboratory

    • Graham D Kosiba

      Lawrence Livermore National Laboratory

    • Matthew P Kroonblawd

      Lawrence Livermore National Laboratory

    • Richard H Gee

      Lawrence Livermore National Lab

    View abstract →