Dr. Christian Reimers

Education

• 2017–2023: PhD in the Computer Vision Group, Friedrich-Schiller-Universität, Jena.
  Thesis title: “Understanding Deep Learning”, (magna cum laude)
• 2013–2017: Master of Science in Mathematics, Georg-August-Universität, Göttingen, 2.0.
  Master Thesis in analytic number theory, Title: “Almost Prime Zeros of Forms”
• 2011–2013: Bachelor of Science in Mathematics, Georg-August-Universität, Göttingen, 2.0.
  Bachelor thesis in analytic number theory, Title: “Hooley’s solution of a problem of Hardy and Littlewood”
• 2003–2010: Abitur, Bernhardt-Riemann-Gymnasium, Scharnebeck, 1.6.

Experience

• 2024 - Present: Project Group Leader, Adapting Machine Learning for Earth Systems Group, Department Biogeochemical Integration, Max Planck Institute for Biogeochemistry, Jena, Germany.
  • Leading the ERC synergy Grant “Understanding and Modelling the Earth System with Machine Learning” Project.
  • Developing deep neural networks for the specific challenges of Earth system science.
  • Combining physical knowledge and data-driven methods in hybrid models.
  • Using methods of causal inference to understand complex dynamics in the earth system.
  • Supervising a postdoc, a PhD, and two bachelor theses, one of which won the “Young Climate Scientist Award 2024”.
• 2021 - 2024: Postdoctoral Researcher, Department Biogeochemical Integration, Max Planck Institute for Biogeochemistry, Jena, Germany.
  • Research Associate on the ERC synergy Grant “Understanding and Modelling the Earth System with Machine Learning”.
  • Developed a machine-learning model for plant phenology.
  • Co-supervised multiple PhD students.
• 2017 - 2021: Research Associate, Computer Vision Group, Friedrich Schiller University Jena and Climate Informatics Group, Institute of Data Science, German Aerospace Center, Jena, Germany.
  • Research Associate on the Topic of "Understanding Deep Learning".
  • Developed a method to understand which features are used by a black-box classifier.
  • Learning unbiased data-driven models from biased datasets.
  • Supervised six interns for up to one year, two bachelor and three master theses.
• 2015 - 2016: Internship, Network Dynamics Group, Max Planck Institute for Dynamics and Self-Organization, Göttingen.
  Internship as a research associate.

Selected Invited Talks

• 2024: Understanding Forest Phenology using Deep Neural Networks, KI-Seminar, University of Applied Sciences Jena, Lecture.
  Link
• 2024: Uncovering the CO₂ Fertilization Effect: Overcoming Challenges in Causal Inference for Earth System Science, Causal inference for time series data Workshop @ UAI 2024, Invited Talk.
  Link
• 2024: The Coolest Kids on the Block: How Diffusion Models can Transform Climate Science, ELLIS/ELISE AI for Learning Weather and Climate, Invited Talk.
  Link
• 2025: Adapting machine learning for atmosphere-biosphere coupling in earth system models, AI for Good, Invited Talk.
  Link

Publications

• 2025: Atmospheric Transport Modeling of CO2 with Neural Networks, Vitus Benson, Ana Bastos, Christian Reimers, Alexander J. Winkler, Fanny Yang, Markus Reichstein, Journal of Advances in Modeling Earth Systems, 17 (2), e2024MS004655.
• 2024: DeepPhenoMem V1.0: Deep Learning Modelling of Canopy Greenness Dynamics Accounting for Multi-Variate Meteorological Memory Effects on Vegetation Phenology, Guohua Liu, Mirco Migliavacca, Christian Reimers, Basil Kraft, Markus Reichstein, Andrew D. Richardson, Lisa Wingate, Nicolas Delpierre, Hui Yang, Alexander J. Winkler, Geoscientific Model Development, 17 (17), S. 6683–6701.
• 2024: Carbon System State Determines Warming Potential of Emissions, Alexander J. Winkler, Ranga Myneni, Christian Reimers, Markus Reichstein, Victor Brovkin, PLOS ONE, 19 (8), e0306128.
• 2024: Optimal Enzyme Allocation Leads to the Constrained Enzyme Hypothesis: The Soil Enzyme Steady Allocation Model (SESAM; v3.1), Thomas Wutzler, Christian Reimers, Bernhard Ahrens, Marion Schrumpf, Geoscientific Model Development, 17 (7), S. 2705 - 2725.
• 2023: Comparing Data-Driven and Mechanistic Models for Predicting Phenology in Deciduous Broadleaf Forests, Christian Reimers, David Hafezi Rachti, Guohua Liu, Alexander Winkler, NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning. Available at: Link.
• 2023: Learning Disentangled Discrete Representations, David Friede, Christian Reimers, Heiner Stuckenschmidt, Mathias Niepert, Machine Learning and Knowledge Discovery in Databases: Research Track, ECML PKDD 2023, Lecture Notes in Computer Science 14172, S. 593 - 609.
• 2023: Hybrid Modeling of Evapotranspiration: Inferring Stomatal and Aerodynamic Resistances Using Combined Physics-Based and Machine Learning, Christian Reimers, Reda ElGhawi, Basil Kraft, Markus Reichstein, Marco Körner, Pierre Gentine, Alexander J. Winkler, Environmental Research Letters, 18 (3), 034039.
• 2023: Understanding Deep Learning, Christian Reimers, PhD Thesis.
• 2022: Investigating Neural Network Training on a Feature Level Using Conditional Independence, Christian Reimers, Niklas Penzel, Paul Bodesheim, Joachim Denzler, European Conference on Computer Vision, Pages 383–399.
• 2021: Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing, Christian Reimers, Paul Bodesheim, Jakob Runge, Joachim Denzler, Pattern Recognition: 43rd DAGM German Conference, DAGM GCPR 2021.
• 2021: Investigating the Consistency of Uncertainty Sampling in Deep Active Learning, Niklas Penzel, Christian Reimers, Clemens-Alexander Brust, Joachim Denzler, Pattern Recognition: 43rd DAGM German Conference, DAGM GCPR 2021.
• 2021: Spatio-temporal Autoencoders in Weather and Climate Research, Xavier-Andoni Tibau, Christian Reimers, Christian Requena-Mesa, Jakob Runge, Deep Learning for the Earth Sciences: A Comprehensive Approach to Remote Sensing, Climate Science, and Geosciences.
• 2021: Conditional dependence tests reveal the usage of ABCD rule features and bias variables in automatic skin lesion classification, Christian Reimers, Niklas Penzel, Paul Bodesheim, Jakob Runge, Joachim Denzler, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.
• 2020: Deep learning – an opportunity and a challenge for geo- and astrophysics, Christian Reimers, Christian Requena Mesa, in Petr Skoda and Fathalrahman Adam, Knowledge Discovery in Big Data from Astronomy and Earth Observation, chapter 13. Elsevier.
• 2020: Determining the Relevance of Features for Deep Neural Networks, Christian Reimers, Jakob Runge, Joachim Denzler, Proceedings of the European Conference on Computer Vision (ECCV).
• 2019: Using Causal Inference to Globally Understand Black Box Predictors Beyond Saliency Maps, Xavier-Andoni Tibau, Christian Requena-Mesa, Christian Reimers, Joachim Denzler, Veronika Eyring, Markus Reichstein, Jakob Runge, International Workshop on Climate Informatics (CI) 2019.
• 2018: SupernoVAE: VAE Based Kernel PCA for Analysis of Spatio-Temporal Earth Data, Xavier-Andoni Tibau, Christian Requena-Mesa, Christian Reimers, Joachim Denzler, Veronika Eyring, Markus Reichstein, Journal Article.