RESEARCH · RESEARCH · #1972
ML postprocessing doubles 2–6 week weather forecast accuracy, paper finds
Researchers including scientists from MIT developed a machine-learning postprocessing model that learns and corrects errors in existing forecasting systems; when applied to a gold-standard model it doubled forecasting accuracy in the 2–6 week (subseasonal) range, placed first in an international forecasting competition, and for the first time beat climatological averages, the team reports in Nature. Coauthors include Judah Cohen, Lester Mackey, Microsoft researchers, ECMWF contributors, and others.
KEY POINTS
- Researchers including scientists from MIT developed a machine-learning postprocessing model that learns and corrects errors in existing forecasting systems; when applied to a gold-standard model it doubled forecasting accuracy in the 2–6 week (subseasonal) range, placed first in an international forecasting competition, and for the first time beat climatological averages, the team reports in Nature.
- Coauthors include Judah Cohen, Lester Mackey, Microsoft researchers, ECMWF contributors, and others.
- Better subseasonal forecasts extend lead time for energy operators, farmers, and emergency managers and improve prediction of extreme events, enabling more effective preparation.
WHY IT MATTERS
Better subseasonal forecasts extend lead time for energy operators, farmers, and emergency managers and improve prediction of extreme events, enabling more effective preparation.