Today鈥檚 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鈥檚 combined need for speed and accuracy taxes even the most modern computers.
The future could take a radically different approach. A collaboration between the 天美影视传媒 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鈥檚 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鈥檚 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 published this summer in the Journal of Advances in Modeling Earth Systems.
鈥淢achine learning is essentially doing a glorified version of pattern recognition,鈥� said lead author , who did the research as part of his UW doctorate in atmospheric sciences. 鈥淚t 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.鈥�
On the left is the new paper鈥檚 鈥淒eep Learning Weather Prediction鈥� forecast. The middle is the actual weather for the 2017-18 year, and at right is the average weather for that day. Weyn et al./ Journal of Advances in Modeling Earth Systems
Although the new model is, unsurprisingly, less accurate than today鈥檚 top traditional forecasting models, the current A.I. design uses about 7,000 times less computing power to create forecasts for the same number of points on the globe. Less computational work means faster results.
That speedup would allow the forecasting centers to quickly run many models with slightly different starting conditions, a technique called 鈥溾�� that lets weather predictions cover the range of possible expected outcomes for a weather event 鈥� for instance, where a hurricane might strike.
鈥淭here’s so much more efficiency in this approach; that’s what’s so important about it,鈥� said author , a UW professor of atmospheric sciences. 鈥淭he promise is that it could allow us to deal with predictability issues by having a model that鈥檚 fast enough to run very large ensembles.鈥�
Co-author at Microsoft Research had initially approached the UW group to propose a project using artificial intelligence to make weather predictions based on historical data without relying on physical laws. Weyn was taking a UW computer science course in machine learning and decided to tackle the project.
鈥淎fter training on past weather data, the A.I. algorithm is capable of coming up with relationships between different variables that physics equations just can’t do,鈥� Weyn said. 鈥淲e can afford to use a lot fewer variables and therefore make a model that’s much faster.鈥�
To merge successful A.I. techniques with weather forecasting, the team mapped six faces of a cube onto planet Earth, then flattened out the cube鈥檚 six faces, like in an architectural paper model. The authors treated the polar faces differently because of their unique role in the weather as one way to improve the forecast鈥檚 accuracy.
The authors then tested their model by predicting the global height of the 500 hectopascal pressure, a standard variable in weather forecasting, every 12 hours for a full year. A recent , which included Weyn as a co-author, introduced WeatherBench as a benchmark test for data-driven weather forecasts. On that forecasting test, developed for three-day forecasts, this new model is one of the top performers.
The data-driven model would need more detail before it could begin to compete with existing operational forecasts, the authors say, but the idea shows promise as an alternative approach to generating weather forecasts, especially with a growing amount of previous forecasts and weather observations.
Weyn is now a data scientist with Microsoft鈥檚 weather and finance division. This research was funded by the U.S. Office of Naval Research and a Department of Defense graduate fellowship.
For more information, contact Durran at drdee@uw.edu or Weyn at jweyn@uw.edu.