Improving Wind Forecasts in the Lower Stratosphere by Distilling an Analog Ensemble Into a Deep Neural Network
Open Access
- 7 August 2020
- journal article
- research article
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 47 (15)
Abstract
We discuss improving forecasts of winds in the lower stratosphere using machine learning to postprocess the output of the European Centre for Medium‐Range Weather Forecasts (ECMWF) Integrated Forecast System. We postprocess global three‐dimensional predictions and demonstrate distilling the analog ensemble (AnEn) method into a deep neural network, which reduces postprocessing 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.Keywords
All Related Versions
This publication has 48 references indexed in Scilit:
- Kalman Filter and Analog Schemes to Postprocess Numerical Weather PredictionsMonthly Weather Review, 2011
- NORA–Nowcasting of Orographic Rainfall by means of AnaloguesQuarterly Journal of the Royal Meteorological Society, 2011
- FlumeJavaACM SIGPLAN Notices, 2010
- The similar days method for predicting near surface wind vectorsMeteorological Applications, 2009
- Probabilistic Quantitative Precipitation Forecasts Based on Reforecast Analogs: Theory and ApplicationMonthly Weather Review, 2006
- Summarizing multiple aspects of model performance in a single diagramJournal of Geophysical Research: Atmospheres, 2001
- Searching for analogues, how long must we wait?Tellus, 1994
- Self-improving reactive agents based on reinforcement learning, planning and teachingMachine Learning, 1992
- A New Look at Weather Forecasting through AnaloguesMonthly Weather Review, 1989
- The predictability of a flow which possesses many scales of motionTellus, 1969