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. 

Wildfires burning in the West affect not only the areas burned, but the wider regions covered by smoke. Recent years have seen hazy skies and hazardous air quality become regular features of the late summer weather. Many factors are causing Western wildfires to grow bigger and to generate larger, longer-lasting smoke plumes that can stretch across the continent. An analysis led by the University of Washington looks at the most detailed observations to date from the interiors of West Coast wildfire smoke plumes. 

In this year of extreme weather events — from devastating West Coast wildfires to tropical Atlantic storms that have exhausted the alphabet — scientists and members of the public are asking when these extreme events can be scientifically linked to climate change. Dale Durran, a professor of atmospheric sciences at the University of Washington, argues that climate science need to approach this question in a way similar to how weather forecasters issue warnings for hazardous weather.