Rice University engineers have developed a deep learning computer system that can accurately predict extreme weather events, like heatwaves, up to five days in advance using minimal information about current weather conditions.
The new network uses an analog method of weather forecasting that computers made obsolete in the 1950s. The Phys.org website reported that the system was fed hundreds of maps that show surface temperatures and air pressures at five kilometers height, and each map shows those conditions several days apart.
The new system is able to make five-day forecasts of extreme weather events like heat waves or winter storms with 85 percent accuracy, the German news agency reported.
Ibrahim Nasrzadeh, study co-author and researcher of mechanical engineering and of Earth, environmental and planetary sciences at Rice University, said: "We decided to train our model by showing it a lot of pressure patterns in the five kilometers above the Earth, and teach it the difference between the air pressures that cause extreme weather changes, and those that don't.”
“Our immediate goal is to extend our forecast lead time to beyond 10 days."
Deep learning is a form of artificial intelligence that relies on "training" computers to make decisions similar to human mind without direct programming. The technology has achieved great success in areas such as facial recognition, self-driving cars and translation.
