Uncertainty Treemaps

Max Sondag, Wouter Meulemans, Christoph Schulz, Kevin Verbeek, Daniel Weiskopf, Bettina Speckmann

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

8 Citations (Scopus)
347 Downloads (Pure)


Rectangular treemaps visualize hierarchical numerical data by recursively partitioning an input rectangle into smaller rectangles whose areas match the data. Numerical data often has uncertainty associated with it. To visualize uncertainty in a rectangular treemap, we identify two conflicting key requirements: (i) to assess the data value of a node in the hierarchy, the area of its rectangle should directly match its data value, and (ii) to facilitate comparison between data and uncertainty, uncertainty should be encoded using the same visual variable as the data, that is, area. We present Uncertainty Treemaps, which meet both requirements simultaneously by introducing the concept of hierarchical uncertainty masks. First, we define a new cost function that measures the quality of Uncertainty Treemaps. Then, we show how to adapt existing treemapping algorithms to support uncertainty masks. Finally, we demonstrate the usefulness and quality of our technique through an expert review and a computational experiment on real-world datasets.

Original languageEnglish
Title of host publication2020 IEEE Pacific Visualization Symposium, PacificVis 2020 - Proceedings
EditorsFabian Beck, Jinwook Seo, Chaoli Wang
PublisherIEEE Computer Society
Number of pages10
ISBN (Electronic)9781728156972
Publication statusPublished - Jun 2020
Event13th IEEE Pacific Visualization Symposium, PacificVis 2020 - Tianjin, China
Duration: 14 Apr 202017 Apr 2020


Conference13th IEEE Pacific Visualization Symposium, PacificVis 2020


  • Human-centered computing
  • Treemaps
  • Visualization
  • Visualization techniques


Dive into the research topics of 'Uncertainty Treemaps'. Together they form a unique fingerprint.

Cite this