Twin Earth Methodologies for Biodiversity, Natural Hazards, and Urbanization

Anthropogenic climate changes pose severe threats to the Earth system, its ecosystems and human society. Effective strategies must be developed to mitigate further adverse changes and adapt to inevitable impacts, particularly the risks arising from an increase in extreme events. In doing so, transformation pathways toward sustainable Earth stewardship urgently need to be identified from global to local scales.
The TUM Innovation Network EarthCare is an explorative and interdisciplinary study that bridges the knowledge gap between the use of Artificial Intelligence and Earth observation data for our planet’s sustainability.

Under this general goal, EarthCare explores three main directions:

- Methodologies for retrieving geoinformation from massive amount of Earth observation data;

- Methodologies for creating hybrid earth system models of compartments of the Earth by combining machine learning and Earth observation data;

- Methodologies and use cases of impact models for decision of sustainability action.

The vision of EarthCare is to provide key methodologies for science and policy-making for a sustainable future.
The research team consists of high profile experts from four disciplines: Earth observation, AI and data science, Earth system modeling, Sustainability, which has unique capabilities to unlock the potential of merging highly innovative methods in Earth observation, artificial intelligence, and Earth system modeling with applications in biodiversity and forestry, the urban domain, and climate-induced natural hazards.

The cross-cutting framework of EarthCare promotes the exchange between key disciplines of climate science and sustainability, and consolidate the scattered expertise in the Munich area.

Our Team

Doctoral theses

  • Deep learning for quantifying the impacts of extreme weather events (Michael Aich)
  • Uncertainty Quantification of Sea Level Rise (Nils Lehmann)
  • Analyzing and Modelling Forest Responses to Drought Stress (Yixuan Wang)


  1. Li, Q., Mou, L., Hua, Y., Shi, Y., Chen, S., Sun, Y., & Zhu, X. X. (2023). 3DCentripetalNet: Building height retrieval from monocular remote sensing imagery. International Journal of Applied Earth Observation and Geoinformation, 120, 103311. 
  2. Li, Q., Krapf, S., Shi, Y., & Zhu, X. X. (2023). SolarNet: A convolutional neural network-based framework for rooftop solar potential estimation from aerial imagery. International Journal of Applied Earth Observation and Geoinformation, 116, 103098. 
  3. Li, Q., Krapf, S., Mou, L., Shi, Y., & Zhu, X. X. (2023). Roof superstructure detection from aerial imagery. In IGARSS 2023-2023 IEEE International Geoscience and Remote Sensing Symposium. IEEE.
  4. Li, Q., Sun, Y., Mou, L., Shi, Y., & Zhu, X. X. (2023). Semi-supervised segmentation of individual buildings from SAR imagery. In 2023 Joint Urban Remote Sensing Event (JURSE). IEEE.
  5. Chen, H., Tuo, Y., Xu, C.Y. and Disse, M., 2023. Compound events of wet and dry extremes: Identification, variations, and risky patterns. Science of The Total Environment, 905, p.167088.
  6. Ho, S., Buras, A., & Tuo, Y. 2023. Comparing agriculture-related characteristics of flash and normal drought reveals heterogeneous crop response. Water Resources Research, 59, e2023WR034994.
  7. Tuo, Y., Wirthensohn M., and Disse, M. Spatio-Temporal Graph Neural Networks for Soil Moisture Drought Forecasting: Adaptability, Predictability, and Interpretability. 11-15 Dec 2023. AGU23.
  8. Tuo, Y., Zhu, X., and Disse, M.: An innovative data driven approach improves drought impact analysis using earth observation data, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-15389.
  9. Hu, X., Tuo, Y., and Disse, M.: Deep learning based coordinates transformations for improving process understanding in hydrological modeling system, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-14631
  10. Ho, S., Buras, A., and Tuo, Y.: A Comparison of Agriculture-related Characteristics of Flash and Traditional Drought, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-1474.
  11. Chen, H., Tuo, Y., and Disse, M.: Intensifying Hydrometeorological Extreme Events and Compound Anomalies in a Temperate Region, Germany , EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-15352.
  12. Wang, Y., Wang, Y., Zhu, X., Rammig, A., Buras, A., Quantifying Tree-species Specific Responses to the Extreme 2022 Drought in Germany, EGU General Assembly 2023, Vienna, Austria, EGU23-6144.
  13. Lehmann, N., Gottschling, N., Depeweg, S., Nalisnick, E., A Comparison of Uncertainty Quantification Methods for Earth Observation Image Regression Data, ICCV Uncertainty in Computer Vision Workshop, 2023.
  14. Zhao, S., Saha, S., Xiong, Z., Boers, N., & Zhu, X. X., Exploring Geometric Deep Learning for Precipitation Nowcasting, IGARSS 2023-2023 IEEE International Geoscience and Remote Sensing Symposium, pp. 3760-3763. IEEE, 2023.
  15. Zhao, S., Xiong, Z., & Zhu, X. X., A Coarse-to-Fine Deep Learning Framework for High-Resolution Future Precipitation Map Generation, EGU General Assembly 2023, Vienna, Austria, EGU23-7751.