Geospatial AI for Air Turbulence Prediction

In the future, Electronic Flight Bags like the one above from The Carbon Project may integrate the results of AI to reduce the danger from air turbulence

According to InformationWeek, "NASA is funding a project run by the National Center for Atmospheric Research (NCAR) in Boulder, Colorado, to identify areas of rapidly developing turbulence and storms over remote areas of the ocean.

The system concept is to guide pilots around these areas and avoid a disaster like the one that killed 228 people in June 2009 when an Air France flight hit a storm and crashed into the Atlantic Ocean. It is not apparent whether the techniques will help guide aircraft around zones of "clear air turbulence" like the one today that bounced Continental Airlines passengers off the ceiling injuring dozens.

According to the article, "Scientists are working to predict areas of turbulence, both in clear skies and within storms, by applying artificial intelligence to satellite data and computer generated models of weather, NCAR scientists said." Scientists analyzing the data use an artificial intelligence technique called "random forests which creates series of yes-or-no votes on how elements of a storm may behave." In the future the information output from these models may become part of online services using spatio-temporal AIXM, WXXM and other Next Generation information.

- Jeff