Statistical learning methods as a basis for skillful seasonal temperature forecasts in Europe

Show full item record

Permalink

http://hdl.handle.net/10138/304582

Citation

Kämäräinen , M , Uotila , P , Karpechko , A , Hyvärinen , O , Lehtonen , I & Räisänen , J 2019 , ' Statistical learning methods as a basis for skillful seasonal temperature forecasts in Europe ' Journal of Climate , vol. 32 , pp. 5363-5379 . https://doi.org/10.1175/JCLI-D-18-0765.1

Title: Statistical learning methods as a basis for skillful seasonal temperature forecasts in Europe
Author: Kämäräinen, Matti; Uotila, Petteri; Karpechko, Alexey; Hyvärinen, Otto; Lehtonen, Ilari; Räisänen, Jouni
Contributor: University of Helsinki, Finnish Meteorological Institute
University of Helsinki, INAR Physics
University of Helsinki, Institute for Atmospheric and Earth System Research (INAR)
Date: 2019-09
Number of pages: 17
Belongs to series: Journal of Climate
ISSN: 0894-8755
URI: http://hdl.handle.net/10138/304582
Abstract: A statistical learning approach to produce seasonal temperature forecasts in western Europe and Scandinavia was implemented and tested. The leading principal components (PCs) of sea surface temperature (SST) and the geopotential at the 150-hPa level (GPT) were derived from reanalysis datasets and used at different lags (from one to five seasons) as predictors. Random sampling of both the fitting years and the potential predictors together with the Least Absolute Shrinkage and Selection Operator regression (LASSO) was used to create a large ensemble of statistical models. Applying the models to independent test years shows that the ensemble performs well over the target areas and that the ensemble mean is more accurate than the best individual ensemble member on average. Skillful results were especially found for summer and fall, with the anomaly correlation coefficient values ranging between 0.41 and 0.68 for these seasons. The correct simulation of decadal trends, using sufficiently long time series for fitting (70 years), and the use of lagged predictors increased the prediction skill. The decadal-scale variability of SST, most importantly the Atlantic multidecadal oscillation (AMO), and different PCs of GPT are the most important individual predictors among all predictors. Both SST and GPT bring equally much predictive power, although their importance is different in different seasons.
Subject: CLIMATE
Decadal variability
EURASIAN SNOW COVER
Europe
Forecast verification
MODES
NORTH-ATLANTIC OSCILLATION
PREDICTION
Principal components analysis
SEA-ICE
SUMMER TEMPERATURE
Seasonal forecasting
Statistical forecasting
VARIABILITY
WEATHER
WINTER
skill
112 Statistics and probability
119 Other natural sciences
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
jcli_d_18_0765.1.pdf 2.698Mb PDF View/Open
seasonal_forecasts_paper_v2.pdf 1.296Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record