Eawag - Swiss Federal Institute of Aquatic Science and Technology

Bridging the gap between data science and mechanistic modelling for a better understanding of community composition.

Data science and mechanistic models for species composition

Deep Neural Networks (DNNs) have shown empirical performance but they are still nevertheless a black-box function modeling data

Universal Aspects of Deep Neural Networks

We test a big data workflow for understanding and predicting plankton dynamics using monitoring data.

Plankifier

Mechanistic modelling of the macroinvertebrate community composition in rivers.

Streambugs

We use machine learning methods to predict the effects of chemicals on aquatic species.

ML Tox

Community detection consists of extracting the affinity between agents of a system, which is extracted from quantities such as the frequency of interactions.

Exposure

Activated dynamics is a very slow process that takes place on exponentially large time scales. Usually it is associated to barrier hopping.

Entropic Activation

We study recent developments in insect abundance, biomass and species richness in terrestrial and aquatic ecosystems of Switzerland.

Analysing recent developments in abundance, biomass and species richness of aquatic and terrestrial insects

Considering uncertainty and ambiguity in societal preferences

Comprehensive uncertainty assessment

Investigating model properties beyond the quality of fit

Metamorphic Analysis of Machine Learning

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).

Contrasting patterns and processes of biological invasions in blue versus green ecosystems

Heterogeneous data platform for operational modeling and forecasting of Swiss lakes in collaboration with the Swiss Data Science Center.

Datalakes - data science forecasts for Swiss lakes

Scalable Bayesian inference framework for uncertainty quantification in stochastic models using thousands of processors in parallel at the Swiss Supercomputing Center and ETH Zurich.

SPUX - High performance environmental data science

Decision support for river management by combining the prediction of effects of suggested measures with quantified societal goals.

AQUACROSS

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.