MIT and Microsoft researchers add ML layer that improves two-to-six-week weather forecasts
Overview
Researchers including MIT's Judah Cohen and Lester Mackey developed a machine-learning layer that corrects errors in existing forecasting models for the two-to-six-week range, according to a Nature paper.
MIT News reports that when applied to ECMWF's model, the layer doubled forecasting accuracy in that window and was the first to beat climatological averages there.
MIT News also says the method improved prediction of extreme weather and is available as an open-source add-on that can be applied to any forecasting model.
Written by AI from the articles below · updated Oct 14, 12:32 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- MIT News · AIOfficialPickMIT and Microsoft researchers improve weather forecasts two to six weeks out
AIResearchers including MIT's Judah Cohen developed a machine-learning layer that corrects errors in existing forecasting models for the two-to-six-week range. When applied to ECMWF's model, it doubled forecasting accuracy in that window and was the first to beat climatological averages there, according to a Nature paper. The article says the method also improved extreme-weather prediction and works as an open-source add-on to any forecasting model.
Heat trend
Not enough continuous observations to show a trend yet.