From Collision to Discovery: Physics Analysis with Apache Spark

31/3-004 - IT Amphitheatre (CERN)

31/3-004 - IT Amphitheatre


Show room on map

Brief description: The LHC experiments continue to produce a wealth of valuable High Energy Physics data, which offer numerous possibilities for new discoveries. The IT Department provides Hadoop and Spark Services and works closely with the experiments and accelerators communities in their quest to analyse and understand these vast amounts of physics and infrastructure data. Big data technologies like Apache Spark show great potential in speeding up the existing procedures. This talk will focus on a number of important questions. How can we use the data produced at the collisions of protons inside the detector to create a histogram that proves the existence of the Higgs boson? What are the problems faced? What are the challenges and the available data sources? How do we perform Physics Analysis with Big Data Technologies? What are the other active use cases on Big Data Analytics at CERN? The attendance of this lecture is optional.

Speaker's short bio: 

Evangelos Motesnitsalis is a Big Data Engineer at the IT Department of CERN. He supports the scientific communities at CERN in their quest to perform big data analytics over physics and accelerator data. He has led the development of the Hadoop-XRootD Connector library, a project that provides direct access of data from XRootD-based storage systems directly into Hadoop and Spark. He is a former Escalation Engineer and Big Data Devops Support Engineer at Amazon Web Services in Dublin, Ireland. He obtained his MSc in Distributed Systems from Imperial College London in 2015 and he has also studied at King's College London and Aristotle University of Thessaloniki.

There is a live webcast for this event