Defense One‚ a publication covering U.S. defense and national security news‚ featured’s ongoing work to accelerate the US Department of Defense (DoD)’s effective use of AI.

Defense One technology editor Patrick Tucker focused on the work is doing with the U.S. Air Force and other agencies‚ describing as an “AI tailor‚ stitching together different methodologies — from simple machine learning to more sophisticated deep learning.’ currently leads nine projects across the DoD including predictive maintenance for multiple USAF platforms‚ intelligence gathering‚ and Mission Data File (MDF) cycle time reduction.

For example‚ the MDFs that inform F-35 Joint Strike Fighter deployments can take the DoD up to 18 months to compile‚ bringing together everything from enemy radar and anti-aircraft missiles to waveforms. Following its contracting of‚ the Pentagon hopes to dramatically shrink the compilation time using artificial intelligence.

Set to complete development next summer‚ the MDF optimization serves as a sort of threat library. In the article‚ President and CTO Ed Abbo explained that‚ “the problem today is that it takes way too long to actually generate that MDF. We can apply the data aggregation capabilities that has and AI to make that process an order of magnitude faster‚ so the data are more current.”

Tucker also discusses the new AI-based tool is creating for intelligence gathering. The project will support the Pentagon to integrate a variety of data from diverse sources to construct a fuller picture‚ similar to the way the brain works to combine sensory input with lived experience and intuition in order to create an understanding of what’s going on.

Highlighting’s predictive maintenance work for aircraft including the E-3 Sentry AWACS‚ the C-5 Galaxy‚ the F-16 Fighting Falcon‚ and soon‚ the F-35 Lightning II‚ Tucker notes how’s technology enables the DoD to predict when a part or computer system might fail on the combined basis of weather‚ deployment‚ mission‚ servicing‚ and the age and condition of its components.

Read the full article here.