Webinar: Delivering the nation’s data with the Open Science Data Federation ft. Brian Bockelman
NSF CI Compass hosted the webinar, "Delivering the nation’s data with the Open Science Data Federation" on Tuesday, September 2, 2025. This webinar featured Brian Bockelman, an investigator at the Morgridge Institute for Research in Madison, Wisconsin and helps lead the Center for High Throughput Computing (CHTC), a research center at the University of Wisconsin-Madison directed by Prof. Miron Livny.
Abstract:
It’s a universal complaint: leveraging the nation’s scientific datasets is Just Too Hard. The data you want is rarely in the same place where you have computing capacity. Accessing data is difficult to automate and requires bespoke tools for each repository you work with. Repositories focus on quality curation – which requires a distinct set of technologies from scaling access to meet compute capacity.
The Open Science Data Federation (OSDF) tackles this problem by providing a service for delivering data that blankets the nation. Repositories can connect to the OSDF through an origin service and, through a series of caches in Internet2, ESNet, and at computing centers, the OSDF can help scale access to meet the user community’s needs, enforce authorization policies, and protect the upstream repository. The OSDF can be combined with other NSF-funded resources such as the OSPool, National Research Platform (NRP), or the National Data Platform (NDP) pilot to provide end-to-end workload management for communities.
Bio:
Brian Bockelman is an investigator at the Morgridge Institute for Research in Madison, Wisconsin and helps lead the Center for High Throughput Computing (CHTC), a research center at the University of Wisconsin-Madison directed by Prof. Miron Livny. Bockelman’s research focuses on advancing distributed High Throughput Computing (dHTC) techniques, particularly in data management, through the practice of Translational Computer Science. He has served for many years in the leadership of the OSG Consortium, the premier national cyberinfrastructure for dHTC and is PI or co-PI on NSF funded projects in the area such as PATh (NSF #2030508), Pelican (NSF #2331480), and IRIS-HEP (NSF #2323298).
