Projects Information Day 2022

By
Swiss Data Science Center
June 1, 2022
Share this post

Collaborative Project Information Day 2022

The goal of the SDSC Collaborative Projects is to help researchers and domain experts leverage the state-of-the-art in data science and at the same time, aim to support the application of techniques developed in research labs working on data science methods to real-world scenarios. The scope of these Collaborative Data Science Projects is representative of the diversity of the research undertaken within the ETH Domain.

In 2022, 14 projects were accepted in the main track, three projects in the Large Scale Infrastructure (LSI) track, and another three projects were co-funded with the Strategic Focus Area on Personalized Health and Related Technologies (PHRT). To learn more about PHRT, click here.

This webinar starts with a presentation of the 6th call. Then, the projects from the 5th call are presented individually.

Replay

  • 00:00 - Presentation of the 6th Call
  • 59:23 - EXPECTmine | Mining Toxicity and High-Resolution Mass Spectrometry Data for Linking Exposures to Effects.
  • 62:10 - ML-SPOCK | Machine Learning Supported system for Performance assessment of steel structures under extreme Operating Conditions and management of risK.
  • 1:04:10 - PHENOMINE | Extracting dynamic ideotypes from seasonal image time series of wheat taken in the field.
  • 1:07:00 - DAAAD_Bridges | Domain-aware-AI Augmented Design of Bridge Structures.
  • 1:09:26 - WATRES | A Data-Driven approach to estimate WATershed RESponses.
  • 1:11:25 - CHEMSPEC | Cost-effective chemical speciation monitoring of particulate matter air pollution.
  • 1:13:35 - PAIREDHYDRO | Machine learning for the components fatigue prediction in hydropower generation.
  • 1:16:55 - DATSSFLOW | Data Science and Mass Movement Seismology: Towards the Next Generation of Debris Flow Warning.
  • 1:19:26 - ML Fusion | Machine Learning for Disruption Prediction in Tokamaks.
  • 1:21:53 - DS4MS | LSI Track | Data Science for Multiplexing Spectrometers.
  • 1:24:04 - LAMP | LSI Track | Lensless Actinic Metrology for EUV Photomasks.
  • 1:26:45 - sc_Drug | co-funded with PHRT | Predictive models of cell type drug sensitivity in Acute Myeloid Leukemia.
  • 1:30:01 - CLIMIS4AVAL | LSI Track | Real-time cleansing of snow and weather data for operational avalanche forecasting.
  • 1:32:08 - DrSCS | co-funded with PHRT| Predicting subclonal drug response from single-cell sequencing for precision oncology.

Speakers

Presentation of the 6th call

  • Dr. Guillaume Obozinski
  • Prof. Fernando Perez-Cruz
  • Dr. Michele Volpi
  • Dr. Ekaterina Krymova
  • Dr. Benjamín Béjar

EXPECTmine

  • Prof. Dr. Juliane Hollender

ML-SPOCK

  • Prof. Dr. Dimitrios Lignos

PHENOMINE

  • Prof. Dr. Achim Walter

DAAAD_Bridges

  • Dr. Ing. Michael Kraus

WATRES

  • Dr. Paolo Benettin

CHEMSPEC

  • Dr. Satoshi Takahama

PAIRED-HYDRO

  • Dr. Elena Vagnoni

DATSSFLOW

  • Dr. Fabian Walter

ML Fusion

  • Dr. Olivier JL Sauter

DS4MS

  • Dr. Daniel Gabriel Mazzone

LAMP | LSI Track

  • Dr. Iacopo Mochi

sc_Drug | co-funded with PHRT

  • Prof. Dr. Didier Trono

CLIMIS4AVAL | LSI track

  • Prof. Dr. Jürg Schweizer

DrSCS | co-funded with PHRT

  • Alexandre Coudray

About the author

Share this post

More blog posts

November 1, 2022

SEMIRAMIS | A new approach to AI-Augmented architectural design

SEMIRAMIS | A new approach to AI-Augmented architectural design

As the world’s cities continue to grow, land is becoming increasingly scarce. However, open space is vital in urban areas. Semiramis is a new approach to AI-augmented architectural design, allowing designers a quick and easy selection of feasible performance values and a qualitative evaluation of the generated geometries.
Blog
April 30, 2021

Dense representation learning

Dense representation learning

Can we extend the concept of word embeddings to any collection of items, possibly unordered? More precisely, can we learn representations from item sets, such as the product baskets in online retail or music playlists on streaming platforms?
Blog
July 9, 2020

CarboSense4D | Modelling CO2 concentration across Switzerland

CarboSense4D | Modelling CO2 concentration across Switzerland

The goal of CarboSense4D is to produce an accurate map of the evolution of carbon dioxide over Switzerland by applying machine learning methods from a network of low-cost sensors.
Blog

More news

June 29, 2017

Open and reproducible environmental science: from theory to equations and algorithms

Open and reproducible environmental science: from theory to equations and algorithms

We need complex models that accurately represent the feedbacks between different processes and compartments to inform us how a perturbation in one component may affect other components of the coupled climate-earth surface system that are relevant to us.
Blog

Contact us

Let’s talk Data Science

Do you need our services or expertise?
Contact us for your next Data Science project!