Cross-institutional research cyberinfrastructure for data intensive science

W. Christopher Lenhardt, Mike Conway, Erik Scott, Brian Blanton, Ashok Kumar Krishnamurthy, Mirsad Hadzikadic, Mladen A. Vouk, Alyson G. Wilson

Abstract: This paper describes a multi-institution effort to develop a “data science as a service” platform. This platform integrates advanced federated data management for small to large datasets, access to high performance computing, distributed computing and advanced networking. The goal is to develop a platform that is flexible and extensible while still supporting domain research and avoiding the walled garden problem. Some preliminary lessons learned and next steps will also be outlined.