Data Science is one of the Strategic Focus Areas defined in the Strategic Planning 2017–2020 for the ETH Domain. The ETH Domain has launched the Initiative for Data Science in Switzerland to accelerate data science through education and research and the provision of infrastructure. This Initiative created the Swiss Data Science Center (SDSC).

About two thirds of the budget are allocated to Data Science Projects that are reviewed on a competitive basis. SDSC Data Science Projects can either focus on the in-depth analysis of a particular interdisciplinary data science problem in a specific scientific domain, or on the development and the implementation of a technology or method that has the potential of broadly enabling data science research.

The first call for SDSC Data Science Projects issued in March 2017 had three motivations:

  • Foster and accelerate the adoption of data science across the ETH Domain: The SDSC is expected to facilitate a strong synergy between data providers, data and computer scientists, and subject-matter experts, fostering scientific breakthroughs with significant societal impact. Projects showing an interdisciplinary character by linking research groups from traditionally separated disciplines are encouraged.
  • Explore the use of or expand on the SDSC hosted platform and services for ETH Domain scientists: The SDSC is developing a highly scalable open software platform (Renga) offering a one-stop-shop for hosting, exploring and analyzing curated, calibrated and optionally anonymized data at scale, at-rest or in-motion.
  • Promote Open (Data) Science: The SDSC platform also offers user-friendly tooling and services to help with the adoption of Open Science, fostering collaboration, research productivity and excellence. Projects are expected to follow guidelines and best practices to enable reusability and reproducibility of research.


The call for proposal received an excellent response: seventy four (74) proposals were submitted. After much consideration and two rounds of reviews (pre-proposal, then full proposals), we carefully selected twelve (12) projects to start either this Fall or next Spring.

An overview of the eight (8) projects to start this fall is presented below. Further updates will be published with the progress of these projects and following to come.



DASH: DAta Science-informed attribution of changes in the Hydrologic cycle

Prof. Reto Knutti (ETH Zürich), Prof. Nicolai Meinhausen (ETH Zürich), Dr. Angeline Pendergrass (NCAR1)

The objective of this project is to provide a new assessment of changes in the water cycle by: (i) detecting occurring changes earlier, (ii) attributing the changes to underlying causes more robustly, (iii) refining the spatial scales of climate change impact assessment associated with the water cycle, (iv) using the emerging signal as an emergent constraint in model evaluation, and (v) providing guidance on future observational needs.

ACE-DATA: ACE Delivering Added-value To Antarctica

Prof. Philippe Gillet (EPFL, Swiss Polar Institute), Prof. David Walton (BAS2), Dr. Julia Schmale (PSI)

The objective of this project is to create a platform to enable the 22 ACE projects to work separately and collaboratively on their own data, linking these individual data-sets with the expedition’s meta-data. Perform a data science research project on a subset of data to gain more holistic view of the ocean and effects on hydrological cycle, chemical composition and heat transport.

crowdAI: an open data science challenge platform integrating with the SDSC

Prof. Marcel Salathé (EPFL)

The objective of this project is integrating crowdAI (open platform for data science challenges) with the SDSC platform (Renga) and running large-scale open data science challenges promoting data science across the country and beyond.

DeepMICROIA: Reducing data needs and improving robustness of deep learning methods for segmentation in microscopic images

Prof. Ender Konukoglu (ETH Zürich), Dr. Anne Bonnin (PSI)

The objective of this projet is to improve the applicability of deep learning based image analysis tools for accurate segmentation of microscopic imaging data by:  (1) Reducing the need for labelled data, (2) Improving robustness to artefacts and (3) Scaling up and distributing developed algorithms.

iLearn: Interpretable Learning Methods for Immunotherapy

Prof. Pascal Frossard (EPFL), Prof. Olivier Michielin (CHUV)

The objective of this project is to develop a new data science framework built on novel neural network architectures, which are able to produce explainable and interpretable models for personalized oncology.

CarboSense4D: Four-dimensional mapping of carbon dioxide using low-cost sensors, atmospheric transport simulations and machine learning

Dr. Dominik Brunner (Empa), Dr. Christina Schnadt Poberaj (ETH Zürich)

The objective of this project is to generate  a high-resolution 4-D product that describes the evolution of CO2 over Switzerland as accurately as possible, by combining sensor data, machine learning, and atmospheric modelling.

SPEEDMIND: Improving species biodiversity analyses and citizen science feedback through mining data

Prof. Niklaus Zimmermann (WSL), Dr. Dirk Karger (WSL), Dr. Damaris Zurell (WSL)

The objective of this project is improving understanding of essential biodiversity drivers and improved predictions of resulting biodiversity patterns in space and time.

DLOC:  Deep Learning for Observational Cosmology

Dr. Tomasz Kacprzak (ETH Zürich), Dr. Aurelien Lucchi (ETH Zürich), Prof. Alexandre Refregier (ETH Zürich), Prof. Thomas Hofmann (ETH Zürich), Dr. Adam Amara (ETH Zürich)

The objective of this project is building on the latest developments in machine learning in order to address three major problems in cosmological analysis: (1) Classification of cosmological models, (2) Generative model for n-body simulations, and (3) Matching simulations to observed data using CNNs.

Sofiane Sarni, Program Manager, Swiss Data Science Center


1 NCAR: National Center for Atmospheric Research, Colorado, USA
2 British Antarctic Survey, UK