The Young Investigator Network is the platform and democratic representation of interests for independent junior research group leaders and junior professors at the Karlsruhe Institut of Technology.

Peer Community
Representation of Interests

Professional Development
Academic Leadership

Individual Support
Funding Opportunities

News

Visit the News Archive to learn more about the archievements of YIN members.

KIT at the Hanover FairSandra Göttisheim (background), Maryna Meretska, KIT
Hanover Fair, April 2: YIN members on Metaoptics and Zero-emission Heating

The Hanover Fair is one of the most important international trade fairs. On April 2nd, two YIN members will present their research on the Tech Transfer Conference Stage (Hall 2, B02): At 1:50 pm, Maryna Meretska will talk about Revolutionary Lightweight and Compact Optical Metagrating quadrupling efficiency at high angles. The technology relies on minute nanostructures to manipulate light instead of heavy and costly lenses. At 2:15 pm, Jingyuan Xu will introduce her research on Pioneering Sustainable Cooling and Heating Solutions for a Greener Future: Based on the elastocaloric effect, certain materials heat up and cool down under mechanical loading and deloading, thus, directly converting mechanical into thermal energy. From March 31 to April 4, both technologies will be presented at the Future Hub (Hall 2, B35).

KIT at Hanover Fair
Surface air temperature climate model projections and observations
A Machine Learning Perspective on Emergent Constraints for Climate Change

Global climate change projections are subject to substantial modelling uncertainties. Any attempt to establish robust relationships between the observable past and simulated future will be hampered by the non-stationary nature of the climate system. In the journal Atmospheric Chemistry and Physics, Peer Nowack and his US colleague Duncan Watson-Parris highlight the validation perspective of predictive skill in the machine learning community as a promising alternative viewpoint. The scientists argue for quantitative approaches in which each suggested constraining relationship can be evaluated comprehensively based on out-of-sample test data – on top of qualitative physical plausibility arguments that are already commonplace in the justification of new emergent constraints.

read more
HochwasserGabriele Zachmann, KIT
BMBF funds AI-based flood forecasting model for small rivers

Floods in small river catchment areas occur quickly and locally in extreme weather conditions. The aim of the joint project "AI-supported flood forecasting for small catchment areas in Germany" is to enable forecasts within up to 48 hours in such situations. The researchers want to create a comprehensive data set in order to train and compare hydro-meteorological forecasting models. Project manager Ralf Loritz believes that here the potential of modern machine learning methods is enormous. They are able to learn complex relationships in data sets and generate robust and computationally efficient simulations based on hydro-meteorological measurement data and numerical weather forecasts. The Federal Ministry of Education and Research (BMBF) funds the project with 1.8 million euros.

Press info