Raytheon Technologies’ intelligence and space business is building explainable machine learning and artificial intelligence systems that could support the missions of users in national security, space, cybersecurity, weather prediction and other high-stakes environments.
The company said Tuesday its AI platforms could help weather forecasters at the National Oceanic and Atmospheric Administration predict the path of hurricanes by recognizing patterns through the use of the ensemble forecasting technique.
David Appel, vice president for command and control digital solutions at Raytheon Intelligence & Space, said the company’s AI technology uses the ensemble modeling technique to help analyze and detect fire patterns during the 2021 California wildfires.
“Our sensors combined with AI could help identify escape routes and ML can optimize looking at fire patterns, where they’re going and how fast they’re going to get there,” said Appel. “It can identify and reroute first responders to be able to rescue men and women who are at risk.”
RI&S teamed up with C3.ai to develop a predictive anomaly detection capability that could enable operators to identify potential problems in satellites and address those issues in advance.
“That’s the power of AI,” Appel said. “We can solve problems before they even appear. And, by keeping systems online and available, agencies can potentially save millions of dollars per satellite.”
Raytheon said the predictive maintenance AI tool uses a machine learning algorithm to track the performance of battery-powered equipment on satellites operating in low-Earth orbit to gather climate and weather measurements for the U.S. government.
“Four years and nearly 3.7 billion records of historical telemetry data were used to create the detection algorithm for this pilot,” said Anthony Bush, director of civil space and weather at RI&S.
“Feeding legacy data from a known event into the AI software enabled us to establish a baseline for success and prove out our hypothesis,” Bush added.