FLARECAST: Big Data und Machine Learning um das Weltraumwetter zu vorhersagen

Event-Datum: 04.04.2017

Ort: FHNW, Hauptgebäude, Klosterzelgstrasse 2, Windisch
Zeit: 12.10 – 13.00 Uhr

Referent
André Csillaghy, Hochschule für Technik / i4DS

FLARECAST: Big Data und Machine Learning um das Weltraumwetter zu vorhersagen

Until recently, solar activity wasn’t considered a notable threat. In the 21st century, however, society has become more vulnerable due to the dependence on increasingly sensitive technologies. Should a strong solar storm hit the Earth, it may not only cause damage to space-based technology, but also to communication systems, transportation networks, pipelines, and power grids on the ground. Reliable space weather predictions are vital for protecting these assets.
The FLARECAST team develops for the European Commission’s Horizon 2020 program a data driven automated forecasting system for predicting solar flares. The system analyses hundreds of thousands of images from the Solar Dynamics Observatory spacecraft to extract with image processing algorithms the most prominent solar flare-predicting parameters. It evaluate those parameters through the use of a variety of machine-learning techniques to identify the best performing ones and eventually use them in quasi real-time predictions.

In our presentation (which will be in German despite this english abstract), we will present the challenges associated with this big data project, and focus on the main responsibilities assigned to FHNW, namely the project’s communication activities, as well as the realisation of the computing infrastructure.

Die Veranstaltung findet im Dozierendenfoyer (Raum 1.145), Gebäude 1, erster Stock, Klosterzelgstrasse 2, Windisch von 12.10 bis 12.45 Uhr mit anschliessender Diskussion bis ca. 13.00 Uhr statt.

Anmeldung
Bitte bis Montag, 3. April 2017, 11.00 Uhr an: sabrina.springmann@fhnw.ch

Sie können auch ein Sandwich (Käse oder Fleisch) mit einem Getränk bestellen.

zurück