deSEO: Physics-Aware Dataset Creation for High-Resolution Satellite Image Shadow Removal

This study evaluates machine learning approaches for upscaling evapotranspiration from the site to the global scale. Sequential models capture temporal dynamics better, especially with precipitation data, but all models show biases in data-scarce regions. Improved upscaling requires richer training data, informed covariate selection, and physical constraints to enhance robustness and reduce extrapolation errors.

We use an innovative approach to studying the Earth's water cycle by integrating advanced machine learning techniques with a traditional water cycle model. Our model is designed to learn from observational data, with a particular emphasis on understanding the influence of vegetation on water movement. By closely aligning with real-world observations, our model offers new possibilities for enhancing our understanding of the water cycle and its interactions with vegetation.

Communicating uncertainties is a crucial yet challenging aspect of spatial modelling – especially in applied research, where results inform decisions. In disaster risk reduction, susceptibility maps for natural hazards guide planning and risk assessment, yet their uncertainties are often overlooked. We present a new type of landslide susceptibility map that visualizes both susceptibility and associated uncertainty alongside guidelines for creating such maps using free and open-source software.

We present a physics-aware machine learning model of the global hydrological cycle. As the model uses neural networks under the hood, the simulations of the water cycle are learned from data, and yet they are informed and constrained by physical knowledge. The simulated patterns lie within the range of existing hydrological models and are plausible. The hybrid modeling approach has the potential to tackle key environmental questions from a novel perspective.