Dr. Alexander Kumpf


Alexander Kumpf worked in the group of Rüdiger Westermann and received his Ph.D. in 2020. His research focused on the visualization of ensemble weather forecast data, machine learning and data mining techiniques such as clustering, dimenionality reduction, statistics, correlation analysis in 3D and tracking of structures. Further, he applied Deep Neural Networks for interpolation and inpainting tasks for scientific data.
His research was conducted within the transregio project Waves to Weather (W2W) funded by the DFG.

Visualizing Confidence in Cluster-based Ensemble Weather Forecast Analyses
Alexander Kumpf, Bianca Tost, Marlene Baumgart, Michael Riemer, Rüdiger Westermann, and Marc Rautenhaus
IEEE Transactions on Visualization and Computer Graphics 2018 (IEEE VIS 2017)

Visual Analysis of the Temporal Evolution of Ensemble Forecast Sensitivities
Alexander Kumpf, Marc Rautenhaus, Michael Riemer, and Rüdiger Westermann
IEEE Transactions on Visualization and Computer Graphics 2019 (IEEE VIS 2018)


Winter Term 2019 / 2020: Data Visualization

Summer Term 2019 - Seminar: How to make A PIXAR movie

Winter Term 2018 / 2019 - Seminar: How to make A PIXAR movie

Summer Term 2018 - Seminar: How to make A PIXAR movie

Supervised Theses

Topic Student Type of Thesis
Analysis and Visualization of Parameter Space Distributions in Multimodal Datasets Josef Stumpfegger Bachelor
Scientific Data Interpolation Using Convolutional Neural Networks Sukanya Raju Master
Correlation Visualization in Parameter-Dependent Ensemble Weather Forecasts Konstantin Rupert Blaschke Bachelor
Multi-Modal Data Visualization using Multi-Parameter Diagrams Patrick Härtl Master
Photon Path Simulation in Volumetric Data Sets Julie Vernet Bachelor
Inpainting sparse Point Cloud Renderings using Convolutional Neural Networks Sangram Gupta Master