Defense Advanced Research Projects AgencyTagged Content List

Analytics for Data at Massive Scales

Extracting information from large data sets

Showing 79 results for Analytics RSS
The rapid pace of new commercial satellite constellation launches has led to a significant increase in the amount and availability of geospatial imagery. Unfortunately, no straightforward way currently exists for analysts to access and analyze all of that imagery. The current ad hoc, time-intensive approach requires gathering and curating data from a large number of available sources, downloading it to specific locations, and running it through separate suites of analytics tools.
The internet of things connects an ever-growing number of smart devices for up-to-the-minute monitoring and tracking of many common events. Head out to most parts of the open ocean, however, and no such capability exists for real-time monitoring of maritime activity.
Picture an intelligence officer in the field. She is trying to piece together a suspected threat, and has access to someone who may have a role in carrying it out. There may be traces of biological or chemical agents on his clothing or hair. She can look for them, but they’re transient, and often present in such low concentrations that she’ll need to send samples to a laboratory. Or she can check his epigenetic markers, read a history of any time he’s been exposed to threat agents, and start piecing together a chain of evidence right there in the field, in real time.
Advanced commercially available technologies—such as additive manufacturing (3-D printing), small-scale chemical reactors for pharmaceuticals, and CRISPR gene-manipulation tools—have opened wide access to scientific exploration and discovery. In the hands of terrorists and rogue nation states, however, these capabilities could be misused to concoct chemical, biological, radiological, nuclear, and high-yield explosive (CBRNE) weapons of mass destruction (WMD) in small quantities and in form factors that are hard to detect.
Rapid comprehension of world events is critical to informing national security efforts. These noteworthy changes in the natural world or human society can create significant impact on their own, or may form part of a causal chain that produces broader impact. Many events are not simple occurrences but complex phenomena composed of a web of numerous subsidiary elements – from actors to timelines. The growing volume of unstructured, multimedia information available, however, hampers uncovering and understanding these events and their underlying elements.
| AI | Analytics | Data |