Academy

Your training network to bridge Earth System and Data Science

Our Summer School - Machine Learning 2023
The 2023 NFDI4Earth Academy Summer School took place from the 12th – 14th June at the FU Berlin and focused on Machine Learning. The fellows at the Academy Kick-Off chose the topic in December 2022. The cohort speakers Melina Knoke and Verena Maleska, as well as Till Fohrmann and Nils Weitzel developed the program in cooperation with the Academy coordinators. 29 Academy fellows attended the Summer School.

The Summer School started on the 12th of June with an introduction to Machine Learning by Christoph Lehmann (TU Dresden), addressing common difficulties within Machine Learning and providing a common baseline of knowledge. Due to the diverse scientific background of the fellows, this topic was of particular interest 

On the 13th of June the day consisted of lectures and hands-on formats on temporal and spatial data. Karin Mora (University Leipzig) gave an overview of temporal data in Machine Learning and provided the fellows with an interesting data set on logistic maps. After lunch, Christopher Kadow (DKRZ) gave an overview of spatial data in Climate Science, and Johannes Meuer (DKRZ) and Maximilian Witte (DKRZ) provided the fellows with a hands-on experience of the topic. The day was closed by presentations from Maria Isabel Arango, Omar Seleem and Josephine Umlauft on Machine Learning in their own research projects. The evening program included a Pub Quiz with exciting and comical questions about the NFDI4Earth and facts about Earth Sciences.

On the 14th of June Maximilian Gelbrecht (TU Munich & PIK) held the final lecture, introducing physics-informed Machine Learning to the fellows.

We use cookies
Some of them are essential for the operation of the site, while others help us to improve this site and the user experience (tracking cookies). You can decide for yourself whether you want to allow cookies or not. Please note that if you reject them, you may not be able to use all the functionalities of the site.