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

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

Exploring the use of machine learning techniques to uncover low-dimensional features within high-dimensional datasets, both simulated and observed

Feature Extraction From High Dimensional Noisy Datasets

Studying interactions between terrestrial avian predators and aquatic fish prey at different spatial scales and their impact on movement, behavior and population dynamics

Spatial dynamics of blue-green predator-prey interactions

Underwater acoustic receivers are widely deployed to study animal movement. We develop state-of-the-art modelling methods for this research.

Modelling for passive acoustic telemetry

We characterize the bi-directional relationships between water resources, refugee migrations and armed conflicts.

Water, armed conflicts and forced migration

We seek to determine why so few international treaties exist over shared aquifers

What does it take to cooperate over transboundary groundwater resources?

Framework to operationalize the human right to water in water extractive industries

Extractive industries and the human rights to water

We develop a mechanistic model to simulate aquatic mesocosms for pesticide risk assessment with a focus on uncertainty quantification.

Mechanistic modelling of Aquatic Mesocosms

From flexible models to process-based networks in hydrology: Using Machine Learning to improve predictions without sacrificing interpretability

Process-based networks in hydrology

Camels-CH: hydro-meteorological time series and landscape attributes in hydrologic Switzerland

Camels Switzerland

Why are some river catchments more sensitive to environmental change than others?

Catchment sensitivity to change

EStreams: An integrated dataset and catalogue of streamflow, hydro-climatic and landscape variables for Europe

EStreams

SuperflexPy: an open-source Python framework for building, testing, and improving conceptual hydrological models

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

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.