Improved very-short-term wind forecasting using atmospheric regimes

Browell, J. and Drew, D. R. and Philippopoulos, K. (2018) Improved very-short-term wind forecasting using atmospheric regimes. Wind Energy. ISSN 1095-4244 (

[thumbnail of Browell-etal-WE-2018-Improved-very-short-term-wind-forecasting-using-atmospheric-regimes]
Text. Filename: Browell_etal_WE_2018_Improved_very_short_term_wind_forecasting_using_atmospheric_regimes.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo

Download (1MB)| Preview


We present a regime-switching vector-autoregressive method for very short-term wind speed forecasting at multiple locations with regimes based on large-scale meteorological phenomena. Statistical methods for wind speed forecasting based on recent observations out-perform numerical weather prediction for forecast horizons up to a few hours, and the spatio-temporal interdependency between geographically dispersed locations may be exploited to improve forecast skill. Here we show that conditioning spatio-temporal interdependency on ‘atmospheric modes’ derived from gridded numerical weather data can further improve forecast performance. Atmospheric modes are based on the clustering of surface wind and sea level pressure fields, and the geopotential height field at the 500hPa level. The data fields are extracted from the MERRA-2 reanalysis dataset with an hourly temporal resolution over the UK, atmospheric patterns are clustered using self-organising maps and then grouped further to optimise forecast performance. In a case study based on 6 years of measurements from 23 weather stations in the UK, a set of three atmospheric modes are found to be optimal for forecast performance. The skill of one- to six-hour-ahead forecasts is improved at all sites compared to persistence and competitive benchmarks. Across the 23 test sites, one-hour-ahead root mean squared error is reduced by between 0.3% and 4.1% compared to the best performing benchmark, and by an average of 1.6% over all sites; the six-hour-ahead accuracy is improved by an average of 3.1%.