Vitus Benson

vitus_benson.png

Hi Friend, great to have you here! :sparkles:

I am Vitus, currently an ELLIS PhD candidate at Max Planck Institute for Biogeochemistry, ELLIS Unit Jena and ETH Zürich. I am conducting my research under the supervision of Markus Reichstein and Fanny Yang.

I train deep neural networks on data of the Earth system. More specifically, I am focusing on two applications. On the one hand, I am interested in the applicability of large-scale AI to Early Warning Systems. Within the EarthNet initiative we are leveraging high resolution satellite imagery to build data-driven impact early warning systems – with applications to anticipatory action for droughts and heat waves. On the other hand, I study the carbon cycle with neural network emulators. In particular, I am assessing the use of AI for atmospheric transport and inverse modeling – analogous to how recent works have revolutionized numerical weather prediction and other areas of scientific machine learning.

My research interests are broadly speaking Deep Learning, Biogeochemistry, Climate Risk Mitigation and Complex Systems. I believe solving global challenges requires working together. Let us do just that!

news

Mar 15, 2025 :bridge_at_night: Early Warning Systems with AI? Check out our recent perspective paper in Nature Communications and the blog posts by Gustau Camps-Valls and Amazon Science!
Feb 13, 2025 :blue_book: In a new study out in JAMES today, we present stable and accurate neural network emulators for atmospheric transport models.
Feb 04, 2025 :cloud: Kick-Off for WeatherGenerator - as part of the Horizon Europe project we develop a foundation model for the land surface.
Jan 30, 2025 :sunrise_over_mountains: During our session at RIMMA2025 - Impact-Based Forecasting and Early Warning Systems Leveraging Machine Learning - I’ll host an interactive game on forecasting rare events!
Jan 28, 2025 :hotsprings: New dataset: DeepExtremeCubes: Earth system spatio-temporal data for assessing compound heatwave and drought impacts - go check it out!
Jan 15, 2025 :clock11: Deadline soon: submit an abstract to our EGU sessions on AI for Early Warning Systems or Carbon Cycle Research!

TEDx talk

selected publications

  1. Nat. Commun.
    reichstein_ncomms_2025.png
    Early warning of complex climate risk with integrated artificial intelligence
    Markus Reichstein* , Vitus Benson* , Jan Blunk , Gustau Camps-Valls , Felix Creutzig , and 14 more authors
    Nature Communications, Mar 2025
  2. JAMES
    benson_james_2024.gif
    Atmospheric Transport Modeling of CO2 with Neural Networks
    Vitus Benson , Ana Bastos , Christian Reimers , Alexander J. Winkler , Fanny Yang , and 1 more author
    Journal of Advances in Modeling Earth Systems, Feb 2025
  3. CVPR
    benson_cvpr_2024.gif
    Multi-modal Learning for Geospatial Vegetation Forecasting
    Vitus Benson , Claire Robin , Christian Requena-Mesa , Lazaro Alonso , Nuno Carvalhais , and 5 more authors
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2024