In February of this year, a commercial pilot flying near Los Angeles International Airport (LAX) spotted a drone about 700 feet away—dangerously close. Fortunately, the plane avoided the drone without incident. Unfortunately, these incidents are becoming far too common.

As of May 2022, the Federal Aviation Administration (FAA), had registered more than 865,000 drones. More than a quarter million remote pilots have been certified to fly drones. And there is growing concern over the proliferation of unmanned aircraft systems (UASs) near U.S. airports.

Working with the FAA systems integrator GDIT developed a UAS Risk Analysis Model that can determine safe flight zones and routes for drones, including altitude and GPS coordinates. The model uses altitude and GPS data to predict flight paths and other data when radar coverage is lacking.

GDIT experts built the system by applying machine learning to massive amounts of geospatial data. Specifically, they analyzed billions of flight path data points at 850 airports around the United States and applied predictive analytics to simulate activity in areas not covered by radar.

Twenty airports plan to evaluate the model when it comes out of production, paving the way for a nationwide implementation at the 30 busiest airports in the United States.

Across the federal government, agencies and their mission partners are using similarly innovative approaches to solve complex and emerging problems – and they’re doing it with data resources they long had in-hand.

The difference is that today advances in machine learning, artificial intelligence, and high-performance computing – to name a few – are dramatically changing what agencies can do with their data.

Here’s another example. This time from the Department of Veterans Affairs (VA).

Working with partners, the VA built a machine learning-based classifier to help physicians spot malignant skin lesions in photos. The agency used computer vision and built deep learning image classification models trained on more than 10,000 images of skin lesions.

The Centers for Medicare and Medicaid Services (CMS) has built machine learning-based models that can identify potentially fraudulent Medicare payments. This is a huge endeavor, with similarly huge impacts.

Consider that in a single day, CMS receives millions of claims representing billions in payments. Using machine learning and regression analysis, link analysis, outlier detection and behavioral analysis the agency was able to identify risky providers and, in turn, analyze large volumes of data that previously went unanalyzed.

“Deriving value from data can transform the way agencies deliver services,” GDIT Vice President, AI and Data Insights Dave Vennergrund said. “Ultimately, this positively impacts the missions they advance and the people they serve.”

Leveraging data to make better, smarter or faster decisions has the potential to transform the way government operates. The tools at agencies’ disposal are as powerful, accessible, and varied as ever before. With them, agencies can support entirely new missions as well as their traditional missions in entirely new ways.

PRESENTED BY