The Data-Intensive Sciences program is concerned with the general problem of dealing with increased data volumes by scientific applications. The applications
have the ability to generate the data, but techniques for dealing with this data --- at both the infrastructure and analysis level --- are most often lacking. The analysis level
is often quite application-specific, but at the infrastructure level most of these applications are quite similar.
In practice, the groups involved with SP1.1 already have a substantial software infrastructure ("problem-solving environment"), however these environments normally assume
execution on a private set of resources with a small, well-controlled user base. One of the main foci and contributions of SP1.1 so far, is to work with these applications to
enable their own software infrastructure to harness the power of the emerging Dutch e-Science grid at the back end.
Bluntly speaking, the main question is "how can we get communities on the dutch e-science infrastructure without a) deploying a dedicated infrastructure and b) forcing them to do
a massive rewrite of their computing framework in order to make use of the generic infrastructure?"
Partners
NIKHEF (Nationaal Instituut voor Kernfysica en Hoge Energiefysica)
SARA Reken- en Netwerkdiensten
ASTRON (Netherlands Foundation for Research in Astronomy)
DANS (Digital Archiving and Networking Services)
MPI for psycholinguistics, Nijmegen
IBM Nederland
Programme leader
Jeff Templon, NIKHEF
templon *AT* nikhef DOT nl
tel: 020 592 2092
People working at SP1.1
Jeff Templon, NIKHEF
Willem van Leeuwen, NIKHEF
Maurice Bouwhuis, SARA
Hanno Holties, ASTRON
Rutger Kramer, DANS
Daan Broeder, MPI Nijmegen
Nicky Hekster, IBM