This study compares the statistical predictability by linear regression of surface wind components using mid-tropospheric predictors with predictability by three nonlinear regression methods: neural networks, support vector machines and random forests. The results, obtained at 2109 land stations, show that more complex nonlinear regression methods cannot substantially outperform linear regression in cross-validated statistical prediction of surface wind components. As well, predictive anisotropy (variations in statistical predictive skill in different directions) are generally similar for both linear and nonlinear regression methods. However, there is a modest trend of systematic improvement in nonlinear predictability for surface wind components with fluctuations of relatively small magnitude or large kurtosis, which suggests weak nonlinear predictive signals may exist in this situation. Although nonlinear predictability tends to be higher for stations with low linear predictability and nonlinear predictive anisotropy tends to be weaker for stations with strong linear predictive anisotropy, these differences are not substantial in most cases. Overall, we find little justification for the use of complex nonlinear regression methods in statistical prediction of surface wind components as linear regression is much less computationally expensive and results in predictions of comparable skill.
Statistical prediction Linear regression nonlinear regression Predictability of surface winds
This is a preview of subscription content, log in to check access.
The authors gratefully acknowledge helpful comments and suggestion from two anonymous reviewers. This research was supported by the Discovery Grants program of the Natural Sciences and Engineering Research Council of Canada.
Amari SI, Murata N, Müller KR, Finke M, Yang HH (1996) Statistical theory of overtraining-is cross-validation asymptotically effective? In: Advances in neural information processing systems, pp 176–182Google Scholar
Csáji BC (2001) Approximation with artificial neural networks. Faculty of Sciences, Eötvös Loránd University, Hungary 24:48Google Scholar
Culver AM, Monahan AH (2013) The statistical predictability of surface winds over western and central Canada. J Clim 26(21):8305–8322CrossRefGoogle Scholar
Davy RJ, Woods MJ, Russell CJ, Coppin PA (2010) Statistical downscaling of wind variability from meteorological fields. Boundary-layer Meteorol 135(1):161–175CrossRefGoogle Scholar
Hastie TJ, Tibshirani RJ, Friedman JH (2009) The elements of statistical learning: data mining, inference, and prediction. Springer, New YorkCrossRefGoogle Scholar
He Y, Monahan A, Jones C, Dai A, Biner S, Caya D, Winger K (2010) Land surface wind speed probability distributions in North America: observations, theory, and regional climate model simulations. J Geophys Res 115(D04):103Google Scholar
Holtslag A, Svensson G, Baas P, Basu S, Beare B, Beljaars A, Bosveld F, Cuxart J, Lindvall J, Steeneveld G et al (2013) Stable atmospheric boundary layers and diurnal cycles: challenges for weather and climate models. Bull Am Meteorol Soc 94(11):1691–1706CrossRefGoogle Scholar
Hsieh WW (2009) Machine learning methods in the environmental sciences: neural networks and kernels. Cambridge University Press, CambridgeCrossRefGoogle Scholar
van der Kamp D, Curry CL, Monahan AH (2012) Statistical downscaling of historical monthly mean winds over a coastal region of complex terrain. II. Predicting wind components. Clim Dyn 38(7–8):1301–1311CrossRefGoogle Scholar
Kanamitsu M, Ebisuzaki W, Woollen J, Shi-Keng Y et al (2002) NCEP-DOE AMIP-II reanalysis (r-2). Bull Am Meteorol Soc 83(11):1631CrossRefGoogle Scholar
Liaw A, Wiener M (2002) Classification and regression by randomforest. R News 2(3):18–22Google Scholar
Mao Y, Monahan A (2017) Predictive anisotropy of surface winds by linear statistical prediction. J Clim 30(16):6183–6201CrossRefGoogle Scholar
Sailor D, Hu T, Li X, Rosen J (2000) A neural network approach to local downscaling of GCM output for assessing wind power implications of climate change. Renew Energy 19(3):359–378CrossRefGoogle Scholar
Salameh T, Drobinski P, Vrac M, Naveau P (2009) Statistical downscaling of near-surface wind over complex terrain in southern France. Meteorol Atmos Phys 103(1–4):253–265CrossRefGoogle Scholar
Stull RB (2000) Meteorology for scientists and engineers: a technical companion book with Ahrens’ Meteorology Today. Brooks/ColeGoogle Scholar
Sun C, Monahan A (2013) Statistical downscaling prediction of sea surface winds over the global ocean. Journal of Climate 7938–7956CrossRefGoogle Scholar
Vapnik V (2013) The nature of statistical learning theory. Springer Science & Business Media, New YorkGoogle Scholar