2D models of the planet used for weather forecasting
Weyn et al./ Journal of Advances in Modeling Earth Systems
First the authors divide the planet’s surface into a grid with a six-sided cube (top left) and then flatten out the six sides into a 2-D shape, like in a paper model (bottom left). This new technique let the authors use standard machine learning techniques, developed for 2-D images, for weather forecasting.

Today’s weather forecasts come from some of the most powerful computers on Earth. The huge machines churn through millions of calculations to solve equations to predict temperature, wind, rainfall and other weather events. A forecast’s combined need for speed and accuracy taxes even the most modern computers.

The future could take a radically different approach. A collaboration between the University of Washington and Microsoft Research shows how artificial intelligence can analyze past weather patterns to predict future events, much more efficiently and potentially someday more accurately than today’s technology.

The newly developed global weather model bases its predictions on the past 40 years of weather data, rather than on detailed physics calculations. The simple, data-based A.I. model can simulate a year’s weather around the globe much more quickly and almost as well as traditional weather models, by taking similar repeated steps from one forecast to the next, according to a paper published this summer in the Journal of Advances in Modeling Earth Systems.

“Machine learning is essentially doing a glorified version of pattern recognition,” said lead author Jonathan Weyn, who did the research as part of his UW doctorate in atmospheric sciences. “It sees a typical pattern, recognizes how it usually evolves and decides what to do based on the examples it has seen in the past 40 years of data.”

Read more at UW News »