Department Systems Analysis, Integrated Assessment and Modelling

Data Science for Environmental Research

We use machine learning and statistical physics methods to tackle problems with large available datasets, and which involve a large number of interacting agents.

Ongoing research projects include:

  • Exploring the impact of toxines on aquatic organisms, predicting the effect of untested toxines on the species, guiding toxicological assessments.
  • The creation of a giant labeled dataset of plankton images and using it to infer the interactions among organisms, and between organisms and environment.
  • The study of the long-time dynamics of high-dimensional systems, from toy models, to deep neural networks and ecosystems.


Dr. Marco Baity JesiTel. +41 58 765 5793Send Mail
Jimeng WuTel. +41 58 765 5996Send Mail


Dr. Marco Baity JesiTel. +41 58 765 5793Send Mail


We test a big data workflow for understanding and predicting plankton dynamics using monitoring data.
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.
Deep neural networks (DNNs) have shown impressive empirical performance but they are still nevertheless a black-box function modeling data.
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.