Ongoing Theses

Deep learning-based, hybrid, uncertainty aware modelling of the coupled water and carbon cycle using Earth observations

Deep Learning for multi-modal characterization of spatio-temporal Earth system dynamics on multiple spatial scales

Interpretable machine learning for hydrological drought understanding

Societal attention to extreme weather events

Compound Extremes and Forest Disturbances

Inter-annual variability in terrestrial ecosystem fluxes

Impacts of extreme weather events across scales and domains

Effects of elevated CO₂ on soil organic matter turnover and nutrient uptake, Institute for Geography, University of Jena

Integrating Remote Sensing and Modeling approaches to Assess Carbon Dynamics of a Fertilized Tree-Grass Ecosystem

Hybrid machine-learning based modelling of biosphere-atmosphere interactions

Environmental controls of ecosystem turnover times

Understanding relationship between ecosystems multifunctionality with climate, vegetation properties and biodiversity

Complex biogeochemical and biophysical properties of tree-grass coexistence at a Mediterranean savanna ecosystem

Biogeochemical insights from multi-tracer atmospheric flask data

Using Flora Incognita plant observation data and applying deep learning for phenological modeling

Deep learning species classification using morphological and genetic data

Ecohydrology from space

Carbon-water interactions across scales

Internally-driven versus externally forced components of the global C cycle

Ecological process understanding across time scales

Forest disturbance classification using deep learning approaches

Revealing Carbon Dynamics in a Semi-Arid Savanna Ecosystem under Different Disturbances

Modelling the role of soil moisture dynamics on soil organic matter decomposition

Atmosphere interactions in seasonally dry systems using lysimeter data

Downscaled Predictions of Climatic Extreme Events

Deep learning approaches for analyzing spatio-temporal memory effects in Earth System data

Machine learning method for vegetation forecasting

Combining process-based and deep learning models to understand soil processes better

Exploring the potential of vegetation information for improving weather forecasts

Data driven models of individual trees to better understand forest water use

Dynamics of the terrestrial carbon and water cycles in response to record shattering eco-meteorological events

Machine-learning based estimation of ecosystem CO₂ fluxes constrained by atmospheric and ecosystem observations

Global Vegetation Dynamics

Land management for ecosystem resilience

Memory effects of climate extremes on ecosystems

How do plant-physiological effects of increasing CO₂ influence the land-atmosphere fluxes of carbon and water?

Plant water use across the globe

Disentangle the individual effects of eCO2 on ET across vegetation types