NASA Uses Machine Learning to Improve Its Whether Forecasts
Hurricane intensity is historically a very difficult thing to predict accurately. One example is Hurricane Patricia in the Northeast Pacific Ocean, which moved from a Category 1 storm into a Catagory 5 within the timeframe of just 24 hours. In order to have more reliable predictions for hurricane intensity, researchers led by scientists at NASA’s Jet Propulsion Laboratory in Southern California are tapping machine learning and artificial intelligence to improve the accuracy of their forecast—especially when it comes to “rapid-intensification events.”
Still in its testing stages, described the AI model in a paper, published on August 25th in the Geophysical Research Letters journal. “It’s an important forecast to get right because of the potential for harm to people and property,” said Hui Su, an atmospheric scientist at JPL.
Image Credit: NOAA