Christina Winkler, M.Sc.


Christina Winkler graduated from Maastricht University in 2017 with a bachelor's degree in Econometrics and Operations Research, focusing on boosting algorithms for learning graphs from high-dimensional time series data in her bachelor thesis. She moved to the University of Amsterdam for a Master's in Artificial Intelligence. Here she developed a super-resolution method using probabilistic generative models (normalizing flows). After her studies, she did an internship at GoPro on image stitching on dual fisheye setups. Subsequently, she worked in education at the University of Amsterdam at the Faculty of Mathematics and Computer Science for the Master's program in Artificial Intelligence. Since April 2021 she is a PhD student at the Department of Remote Sensing Methodology at TUM.


Focus and Interests

  • Probabilistic Generative Models (Normalizing Flows)
  • Change Detection
  • Incremental & Curriculum Learning


Global Earth Monitor

The Global Earth Monitor (GEM) project is addressing the challenge of continuous monitoring of large areas in a sustainable and cost-effective way. The goal of the project is to establish a new disruptive Earth Observation Data: Exploitation model which will dramatically enhance the utilisation of Copernicus data.



  • ElGhawi, Reda; Kraft, Basil; Reimers, Christian; Reichstein, Markus; Körner, Marco; Gentine, Pierre; Winkler, Alexander J: Hybrid modeling of evapotranspiration: inferring stomatal and aerodynamic resistances using combined physics-based and machine learning. Environmental Research Letters 18 (3), 2023, 034039 more…
  • Christina Winkler, Daniel E. Worrall, Emiel Hoogeboom and Max Welling: Learning Likelihoods with Conditional Normalizing Flows. University of Amsterdam, 2019, more…