I’m happy to share that I’ve successfully defended my Ph.D. thesis with the title Quantitative Methods for Uncertainty Visualization.
My work aims to tackle two research questions:
“How can we communicate uncertainty with its statistical properties?” and “How to adapt visualization methods to uncertainty?”
To answer these questions, my thesis explores novel techniques ranging from visualizing uncertain hierarchical data and networks, to dimensionality reduction under uncertainty. By doing so, we investigate how to propagate uncertainty through the various stages of the visualization pipeline. As a result, we identify two different frameworks: analytical propagation and uncertainty propagation through sampling. My thesis shows how the former helps us better understand the sensitivity of visualizations to uncertainty in the data, while the latter provides great flexibility for handling arbitrary models of uncertainty.
You can find my thesis through KOPS.
I’ve been very fortunate to have great collaborators and coauthors with whom I worked together on these topics. I’m very grateful to my advisors – Oliver Deussen and Daniel Weiskopf of the SFB-TRR 161. And to Christoph Schulz, who is working with me on project A01.