MATCH to Provide Visibility of CBRNE Threats
BAE Systems is to develop advanced analytics technology under a contract from the US Defense Advanced Research Projects Agency’s (DARPA) Defense Sciencc Office to assist in the detection and deterrence of mass destruction activity, helping to protect national security, the company announced on 12 February.
The first-of-its-kind technology will leverage multiple data sources and uses data fusion, adversary modelling, pattern matching and machine learning techniques to detect and identify indications of chemical, biological, radiological, nuclear and explosive (CBRNE) threat.
As part of DARPA’s SIGMA+ programme, the BAE Systems FAST Labs research and development team will work with partners Barnstorm Research and Washington State University to create a technology solution called Multi-info Alerting of Threat CBRNE Hypotheses (MATCH). The solution will automatically populate a world graph using sensor and multi-source data to provide analysts with visibility of threat activities in a metropolitan region. Using the graph, MATCH will create hypotheses that identify and characterise threatening CBRNE activity.
“Our technology aims to help analysts close the loop between the analysis of information and the collection of new information to fill in the gaps and provide a comprehensive picture of a potential threat,” explained Chris Eisenbies, Product Line Director of the Autonomy, Controls and Estimation group at BAE Systems. “Most importantly, our solution automates a process that is currently manually intensive, improving an analyst’s ability to quickly and accurately identify CBRNE activity and ultimately, helping to protect our country from these significant dangers.”
Phase 1 research on the SIGMA+ program leverages BAE Systems’ expertise in data fusion, advanced analytics and resource management as part of its autonomy technology portfolio. It also builds on previous work for DARPA’s Insight programme and leverages the company’s mature All-Source Track and Identity Fuser (ATIF) and Multi-INT Analytics for Pattern Learning and Exploitation (MAPLE) technologies.
