Big Data and Science: Infrastructure and Services
Overview
Data is now considered the “Fourth Paradigm” in Science. This shift is being driven by: the rapid growth in data from improvements in scientific instruments such as sequencers and advanced imaging technologies; increasing emphasis on sharing and collaborating on data; and the growing ability to drive discovery directly from data. Data Intensive Scientific computing touches on all the Five “V’s” (Volume, Velocity, Variety, Veracity, and Value) associated with Big Data. But scientific data and processes used to analyze the data are substantially different from those encountered in the Enterprise or Web 2.0 space. This workshop’s goals are multi-fold. We will focus on capturing the cutting edge research to date that is enabling the scientific community to address their data challenges and opening up new avenues of scientific discovery. Second, we will engage the scientific community in understanding their big data challenges and problems. Finally, we will identifying gaps in current technologies available in the Web 2.0 space as well as identify future computer science research challenges. Our topics of interest will span the range from new hardware architectures optimized for science, to emerging frameworks , to science-driven services. The workshop will provide a venue for participants to showcase innovative tools and services, build new collaborations, and hear from application scientists about the challenges they face. The workshop will consist of a mix of paper presentations, panels and invited speakers.
We believe that IEEE Big Data Conference is an ideal venue for this workshop because of the relevance of the topic and the ability to engage a wider community across academia, research labs and industry. There are a couple of other related workshops but their focus is different from the one we propose. For example, ScienceCloud and DataCloud focus on scientific applications and big data problems specifically in cloud environments
Topics of Interest
We invite submissions of original work on the following topics. Papers can be either short (4 page position papers) or longer (8 pages) research papers. The submission are expected to clearly describe how the technology has considered the unique needs of Science in their research, design, and development.
Big Data in Science needs and requirements, and use cases
Service Infrastructure in development and deployed at facilities
Hardware architectures supporting big data in science
Networking and file system support for big data in science
Software tools, frameworks and methodologies for handling big data in scientific applications
Use of Big Data technologies (e.g., Hadoop and NoSQL) for science
Important Dates
May 30 , 2013: Call for Workshops Papers will distributed
July 30, 2013: Due date for full workshop papers submission
August 20, 2013: Notification of paper acceptance to authors
September 10, 2013: Camera-ready of accepted papers
October 6-9, 2013: Workshop
Program Chairs
Shane Canon (LBNL)
Chaitanya Baru (UCSD)
Ian Foster (ANL)
Program Committee:
TBD
Invited Keynote and Panel Speakers/Topics
Check back to see the list of Invited Speakers.
Agenda:
Subject to change
| Time | Topic |
|---|---|
| 9:00 | Introduction |
| 9:15 | Invited Talks (Maybe 1 “Keynote” style) |
| 10:00 | Paper Presentations (25 minute each, so three) |
| 12:00 | Lunch |
| 1:00 | Invited Talks |
| 2:00 | Paper Presentations cont'd |
| 4:00 | Lightning Talks (nine 5 minute talks) |
| 4:45 | Discussion |
| 5:00 | Best Paper and Close Out |
