Data-Driven Discovery Initiative
Pre-Applications Due February 24, 2014 by 5 pm Pacific Time.
15 Awards at $1,500,000 each, at $200K-$300K/year for five years.
From the post:
Our Data-Driven Discovery Initiative seeks to advance the people and practices of data-intensive science, to take advantage of the increasing volume, velocity, and variety of scientific data to make new discoveries. Within this initiative, we’re supporting data-driven discovery investigators – individuals who exemplify multidisciplinary, data-driven science, coalescing natural sciences with methods from statistics and computer science.
These innovators are striking out in new directions and are willing to take risks with the potential of huge payoffs in some aspect of data-intensive science. Successful applicants must make a strong case for developments in the natural sciences (biology, physics, astronomy, etc.) or science enabling methodologies (statistics, machine learning, scalable algorithms, etc.), and applicants that credibly combine the two are especially encouraged. Note that the Science Program does not fund disease targeted research.
It is anticipated that the DDD initiative will make about 15 awards at ~$1,500,000 each, at $200K-$300K/year for five years.
Pre-applications are due Monday, February 24, 2014 by 5 pm Pacific Time. To begin the pre-application process, click the “Apply Here” button above. We expect to extend invitations for full applications in April 2014. Full applications will be due five weeks after the invitation is sent, currently anticipated for mid-May 2014.
If you are interested in leveraging topic maps in your application, give me a call!
As far as I know, topic maps remain the only technology that documents the basis for merging distinct representations of the same subject.
Mappings, such as you find in Talend and other enterprise data management technologies, is great, so long as you don’t care why a particular mapping was done.
And in many cases, it may not matter. When you are exporting one time mailing list for a media campaign. It’s going to be discarded upon use so who cares?
In other cases, where labor intensive work is required to discover the “why” of a prior mapping, documenting that “why” would be useful.
Topic maps can document as much or as little of the semantics of your data and data processing stack as you desire. Topic maps can’t make legacy data and data semantic issues go away, but they can become manageable.