Bridging the gap between data science and mechanistic modelling to gain knowledge about community assembly
Heterogeneous data platform for operational modeling and forecasting of Swiss lakes in collaboration with the Swiss Data Science Center.
Deep Neural Networks (DNNs) have shown empirical performance but they are still nevertheless a black-box function modeling data
Scalable Bayesian inference framework for uncertainty quantification in stochastic models using thousands of processors in parallel at the Swiss Supercomputing Center and ETH Zurich.
We test a big data workflow for understanding and predicting plankton dynamics using monitoring data.
Mechanistic modelling of the macroinvertebrate community composition in rivers.
We compare invasions in aquatic and terrestrial ecosystems primarily at large (national) spatial scales and among several higher-level taxa (insects, molluscs, crustaceans, all major vertebrate classes, and plants).
We use machine learning methods to predict the effects of chemicals on aquatic species.
Community detection consists of extracting the affinity between agents of a system, which is extracted from quantities such as the frequency of interactions.
Activated dynamics is a very slow process that takes place on exponentially large time scales. Usually it is associated to barrier hopping.
Decision support for river management by combining the prediction of effects of suggested measures with quantified societal goals.
We investigate human impacts on the community composition of macroinvertebrates and fish in Swiss rivers with statistical analyses of existing monitoring data, food web analyses, and computer models.
Understanding trout meta-populations in river networks and predicting the effects of habitat restoration measures.
Complex systems theory meets big phytoplankton trait data.
Development of unified ecological assessment procedures for river management.
Restoring rivers for for effective catchment management.
Hypothesis testing using controlled experiments to characterize diffuse pollution in small agricultural catchments
Towards a better understanding and more reliable predictions of complex systems dynamics.
Development of a dynamical model to simulate the water and water related energy flows in function of time.
Development of a semi-distributed hydrological model with a “flexible” approach. Testing and comparing of different model structures to combine modeling and experimenting into a learning process.
Calibrating stochastic rainfall-runoff models to scaling laws, for improved predictions of extreme events.
A tool kit is being developed to perform multiple tasks for climate change purposes.
Flexible framework for conceptual hydrological modeling.
The agro-hydrologic SWAT model is coupled with the water allocation optimization model MODSIM.
With continuing population growth, increasing affluence and economic development, and diet change towards more meat consumption, the demand for food will also increase.