37. SCIENTIFIC
VISUALIZATION AND DATA UNDERSTANDING
Scientific visualization and data management are critical
enabling technologies for computational science research, which provide
scientists with the capability to extract the scientific insights from data sets
generated by simulations and experiments. The
visualization systems that are sought must be attuned to the needs of domain
scientists and be integrated with important data management and domain-specific
science. In addition, to be part of
a useful investigatory scientific research environment, visualization systems
and data analytics must further be integrated with supporting computational
science technologies such as petascale computing, data management and
storage/retrieval; I/O capabilities, and networking capabilities for remote
visualization.
a. Scientific
Visualization and Management—Scientific discoveries enabled by petascale
computational sciences require advanced visualization systems to extract the
scientific insights from data generated by simulation and experiments.
With petascale computing and other experiments expected to generate
several petabyte of unstructured multi-dimensional data sets per year,
next-generation scientific visualization systems will outstrip the performance
of today’s systems. Next-generation
data analytics will be needed to: 1)
compare data between different simulation runs, 2) perform statistical analysis
on data, 3) perform comparison between simulation data and experimental data,
and 4) accommodate uncertainties in data. Grant
applications in this subtopic should focus on, but are not limited to:
1) parallel visualization tools and services, 2) tools to enable
knowledge discovery at petascale, 3) GPU programming model to multi-GPU systems,
4) high-level I/O libraries optimized for large-scale scientific visualization,
5) full-feature visualization tools for unstructured data, and 6) uncertainty
management in scientific visualization.
Questions – contact Thomas Ndousse-Fetter (tndousse@science.doe.gov)
b. Petabyte-Scale
Data Transformation, Discovery, and Distribution—Science is increasingly becoming more and more data-intensive.
In many large-scale scientific experiments and simulations, the data
challenge already exceeds the compute-challenge in its needed resources.
The scientific importance of storing, discovering, and distributing
scientific data on an unprecedented scale to scientists in different
geographical locations is clear—it is the limiting or enabling factor of
scientific discoveries in many large-scale data-intensive science involving
distributed resources and research teams. Grant
applications are sought to focus on the development of scalable tools to
facilitate the transformation, discovery, and distribution of scientific data
(unstructured data). These include
but are not limited to: 1)
high-speed data transfer protocols and services optimized for optical links, 2)
salable tools for storage systems coordination and scheduling, 3) metadata and
data replication services to support data distribution, and 4) tools to
interface data management systems to network and storage systems. Grant
applications focusing on commercial database management extension are beyond the
scope of this subtopic and will not be peer-reviewed.
Questions
– contact Thomas Ndousse-Fetter (tndousse@science.doe.gov)
References:
1. Bunn, J. and Newman, H., “Data-Intensive Grids for High-Energy Physics,” Grid Computing, Making the Global Infrastructure a Reality, Berman, Fox and Hey, eds., UK: Wiley, 2003. (ISBN: 0-470-85319-0)
2. “Planning ASCR/Office of Science Data-Management Strategy,” Data Management Challenge Workshop Report, 2004. (Full text available at: http://www-conf.slac.stanford.edu/dmw2004/docs/DM-strategy-final.doc)
3.
Childs, H. and Miller, M., “Beyond
Meat Grinders: An Analysis Framework
Addressing the Scale and Complexity of Large Data Sets,”
Proceedings of SpringSim High
Performance Computing Symposium (HPC 2006), Huntsville, AL, April 2-6, 2006,
pp. 181-186, 2006. (Full text
available at: http://graphics.idav.ucdavis.edu/publications/print_pub?pub_id=891)
6. Visualization Research Activities at Pacific Northwest National Laboratory, at http://www.pnl.gov/news/experts/visualization.stm
Return to the Complete List of Topics
| Program Information, Instructions and Requirements | Technical Topic Descriptions | Download Program Information | Download Technical Topics |