Machine learning for data-driven visualization (ML4Vis)

PN 6-6

Project description

This project addresses the research problem of using machine learning (ML) for visualization (ML4Vis). We will develop visualization methods that employ a data-driven approach for feature specification and extraction in the context of multifield data. For this, we will especially use Neural Network architectures and formulate our visualization tasks as supervised learning problems. Our visualization presents identified characteristics of interest when applying trained models to the data, or uses the models for selecting and directly generating expressive visual representations for data analysis. This research directly tackles a fundamental challenge in visualization: meaningful data reduction and abstraction are required, yet solely relying on manual specification by the user is increasingly impractical considering the growing data size and complexity from simulations and experiments. The developed approaches will be applied together with SimTech collaborators to help them analyze, understand, and discover new characteristics in their data.

Project information

Project title Machine Learning for Data-driven Visualization (ML4Vis)
Project leaders Thomas Ertl (Ingo Steinwart)
Project duration January 2019 - June 2022
Project number PN 6-6

Publications PN 6-6

  1. 2023

    1. A. Straub, G. K. Karch, J. Steigerwald, F. Sadlo, B. Weigand, and T. Ertl, “Visual Analysis of Interface Deformation in Multiphase Flow,” Journal of Visualization, vol. 26, Art. no. 6, 2023, doi: 10.1007/s12650-023-00939-x.
    2. A. Straub, N. Karadimitriou, G. Reina, S. Frey, H. Steeb, and T. Ertl, “Visual Analysis of Displacement Processes in Porous Media using Spatio-Temporal Flow Graphs,” IEEE Transactions on Visualization and Computer Graphics, 2023, doi: 10.1109/TVCG.2023.3326931.

  2. 2022

    1. G. Tkachev, R. Cutura, M. Sedlmair, S. Frey, and T. Ertl, “Metaphorical Visualization: Mapping Data to Familiar Concepts,” in CHI Conference on Human Factors in Computing Systems Extended Abstracts, ACM, Apr. 2022. doi: 10.1145/3491101.3516393.
    2. A. Straub, S. Boblest, G. K. Karch, F. Sadlo, and T. Ertl, “Droplet-Local Line Integration for Multiphase Flow,” in 2022 IEEE Visualization and Visual Analytics (VIS), 2022, pp. 135–139. doi: 10.1109/VIS54862.2022.00036.
    3. S. Frey et al., “Visual Analysis of Two-Phase Flow Displacement Processes in Porous Media,” Computer graphics forum, vol. 41, Art. no. 1, 2022, doi: 10.1111/cgf.14432.

  3. 2021

    1. A. Straub, G. K. Karch, F. Sadlo, and T. Ertl, “Implicit Visualization of 2D Vector Field Topology for Periodic Orbit Detection,” in Topological Methods in Data Analysis and Visualization VI, I. Hotz, T. Bin Masood, F. Sadlo, and J. Tierny, Eds., in Mathematics and Visualization. , Springer International Publishing, 2021, pp. 159–180. doi: 10.1007/978-3-030-83500-2_9.
    2. G. Tkachev, S. Frey, and T. Ertl, “S4: Self-Supervised learning of Spatiotemporal Similarity,” IEEE Transactions on Visualization and Computer Graphics, 2021.
    3. M. Heinemann, S. Frey, G. Tkachev, A. Straub, F. Sadlo, and T. Ertl, “Visual analysis of droplet dynamics in large-scale multiphase spray simulations,” Journal of Visualization, vol. 24, Art. no. 5, May 2021, doi: 10.1007/s12650-021-00750-6.
    4. K. Schatz et al., “2019 IEEE Scientific Visualization Contest Winner: Visual Analysis of Structure Formation in Cosmic Evolution,” IEEE Computer Graphics and Applications, vol. 41, Art. no. 6, 2021, doi: 10.1109/MCG.2020.3004613.

  4. 2019

    1. G. Tkachev, S. Frey, and T. Ertl, “Local Prediction Models for Spatiotemporal Volume Visualization,” IEEE Transactions on Visualization and Computer Graphics, 2019, doi: 10.1109/TVCG.2019.2961893.
    2. I. Tabiai et al., “Hybrid image processing approach for autonomous crack area detection and tracking using local digital image correlation results applied to single-fiber interfacial debonding,” Engineering Fracture Mechanics, vol. 216, p. 106485, 2019, doi: 10.1016/j.engfracmech.2019.106485.
To the top of the page