TERRAIN: Temporal Exploitation and Reasoning using Resource-Activity Inference Networks

Detecting targets and predicting threat networks hidden in high volume all-source intelligence is a central challenge in the intelligence Processing, Exploitation and Dissemination (PED) cycle. Failure to maintain a common picture and shared situational awareness across disparate sensor products can result in enormous information loss, placing the entire team and intelligence community at a severe disadvantage. By improving the tasking of sensors, only the most salient intelligence will be collected, thus reducing the volume of data to be analyzed and optimizing the PED cycle. Aptima proposes to develop Temporal Exploitation and Reasoning using Resource-Activity Inference Networks (TERRAIN), an integrated system for Tasking, Collection, Processing, Exploitation and Dissemination (TC-PED). TERRAIN system will innovatively combine three critical functions in support of Marine Corps missions: active sensor stream analysis, threat situation estimation, and sensor allocation planning to produce a sensor tasking system that maximizes limited resources by identifying gaps in the current coverage and forecasting where future sensor coverage need will be greatest. Designed with Hadoop"s Map-Reduce Architecture for integration to a cloud-based computing environment, TERRAIN will be a lightweight, online system that scales to a high volume of streaming, multi-intelligence sensor feeds.