Raytheon creates explainable AI tools to predict weather and satellite issues; David Appel quoted

0

The intelligence and space activity of Raytheon Technologies is growing explainable machine learning and artificial intelligence systems that could support user missions in national security, space, cybersecurity, weather forecasting and other high-stakes environments.

The company said on Tuesday that its AI platforms could help forecasters from the National Oceanic and Atmospheric Administration predict the trajectory of hurricanes by recognizing patterns through the use of the ensemble forecasting technique.

David Appel, vice president of digital command and control solutions at Raytheon Intelligence & Space, said the company’s AI technology uses ensemble modeling technique to help analyze and detect patterns of fire during the 2021 California wildfires.

“Our sensors combined with AI could help identify escape routes and the ML can optimize the examination of fire patterns, their direction and the speed at which they will get there,” said Appel. “He can identify and redirect first responders so they can rescue men and women at risk. “

RI&S has partnered with C3.ai to develop a predictive anomaly detection capability that could allow operators to identify potential problems in satellites and resolve those issues in advance.

“That’s the power of AI,” Appel said. “We can fix problems before they even appear. And, by keeping the systems online and available, agencies can potentially save millions of dollars via 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 collect climate and weather measurements for the U.S. government.

“Four years and nearly 3.7 billion historical telemetry data records were used to create the detection algorithm for this pilot,” said Anthony Bush, director of civil space and weather at RI&S .

“Feeding the data inherited from a known event into AI software allowed us to establish a baseline for success and prove our hypothesis,” Bush added.

Share.

Comments are closed.