The SKA observatory (SKAO)will provide scientists with a wide variety of data of a quality and quantity that goes far beyond anything currently provided by radio observatories.
To prepare the science community, data challenges between scientific teams from all over the world are organised. For the second edition of the SKA Data Challenges (SDC), a French team led by the Observatoire de Paris - PSL with CNRS, Observatoire de la Côte d'Azur and several French universities won the gold medal in the competition on the Jean Zay machine of GENCI/IDRIS. The second edition of this challenge, SKADC2, was a new step for the whole community to learn together about the common efforts to be undertaken.
GENCI is extremely proud to have participated by providing accelerated computing resources from the #JeanZay supercomputer - one of the three French national supercomputers - to 5 teams involved in the challenge, in a coordinated manner with the expert support of IDRIS/Centre national de la recherche scientifique (CNRS) and the Observatoire de la Côte d'Azur!
The MINERVA team from Observatoire de Paris | PSL with the Centre national de la recherche scientifique (CNRS) and partners from the Canadian Institute for Theoretical Astrophysics and the Strasbourg Astronomical Observatory, won this challenge after using an innovative approach based on machine learning performed on the GENCI-IDRIS/Centre national de la recherche scientifique supercomputer.
“While 1,000 hours of GPU computing resources have been allocated by IDRIS to the MINERVA project to enable the development of a machine learning method in order to better suit the needs of astronomical images, this success heralds very promising future developments between HPC/AI and large-scale scientific instruments in the framework of the SKA project, in line with GENCI’ strategic plan” says Philippe Lavocat Chairman and CEO of GENCI.