Improving Wind Forecasts in the Lower Stratosphere by Distilling an
Analog Ensemble into a Deep Neural Network
Abstract
We discuss improving forecasts of winds in the lower stratosphere using
machine learning to post-process the output of the European Centre for
Medium-Range Weather Forecasts (ECMWF) Integrated Forecast System. We
post-process global three-dimensional predictions, and demonstrate
distilling the analog ensemble (AnEn) method into a deep neural network
which reduces post-processing latency to near zero maintaining increased
forecast skill. This approach reduces the error with respect to ECMWF
high-resolution deterministic prediction between 2-15% for wind speed
and 15-25% for direction, and is on par with ECMWF ensemble (ENS)
forecast skill to hour 60. Verifying with Loon data from stratospheric
balloons, AnEn has 20% lower error than ENS for wind speed and 15% for
wind direction, despite significantly lower real-time computational cost
to ENS. Similar performance patterns are reported for probabilistic
predictions, with larger improvements of AnEn with respect to ENS. We
also demonstrate that AnEn generates a calibrated probabilistic
forecast.