Pentagon looks to apply AI to powerful mapping radar

The Pentagon is seeking information from industry on how to apply artificial intelligence, machine learning and deep learning models to synthetic aperture radar, according to a new online notice.

In a May 1 request for information, the Pentagon's Joint Artificial Intelligence Center asks for input "on technologies or corporate capabilities that can develop an AI/ML/Deep Learning algorithmic model(s) utilizing capabilities unique to Synthetic Aperture Radar (SAR)." The center is seeking responses by May 25.

"The JAIC is searching for capabilities of providing imagery within any meteorological medium, regardless of density, depth, type of geological, geographical or meteorological landscape, or event and/or time of day for the purposes of providing situational awareness for damage assessment," the notice states.

The project is being run under the center's humanitarian assistance and disaster relief "national mission initiative." The initiative's efforts have centered on applying AI and machine learning to disaster response operations, like detecting fire lines in California and assessing flood damage following hurricanes.

JAIC officials want to understand how the SAR models can complement the center's "existing sensor suite of models for building damage assessment, flood plane analysis, road obstruction identification and any other imagery-based solutions for our humanitarian and disaster relief product lines," according to JAIC spokesman Lt. Cmdr. Arlo Abrahamson.

"We are seeking information on how and to what degree we can integrate sensor results into a 'Common Operating Imagery-based Picture' and then use algorithmic models to scale, size, scope and integrate into existing platforms or platforms currently in development," Abrahamson told Inside Defense in an email.

SAR uses the flight path of a side-looking radar to electronically simulate a large array, capable of generating high-resolution, three-dimensional images. According to the JAIC notice, SAR could be used to create flood maps, assess deformation of the ground due to earthquakes, map wildfire areas, detect tunneling and monitor deforestation, among other tasks.

SAR can be carried by both aircraft and spacecraft. "We will be considering both platforms and their potential for use in these models," Abrahamson said.