Abstract
Machine learning is very popular in the environmental modelling community and has recently been demonstrated to be a useful tool for wind resource assessment as well. Despite the popularity of wind resource assessment, research in the field of machine learning for this purpose is in its infancy. Only few algorithms have been tested and only for specific areas, making it difficult to draw any conclusions in regards to the best wind estimation method at the global scale. In this study, we compared several machine learning algorithms with validation techniques specifically employed to not only assess their accuracy but also their transferability. In particular, we tested cross-validation techniques designed to test the accuracy of the estimation in the context of autocorrelation. This way we performed a benchmarking experiment that should provide end users with practical rules of application for each algorithm. We tested three families of popular algorithms, namely linear models, decision trees and support vector machines; each was tested using wind mean speed data and several environmental covariates as predictors. The results demonstrated that no single algorithm could consistently be used to estimate wind globally, even though decision-tree based methods seemed to be often the best estimators.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Argyle P, Watson SJ (2014) Assessing the dependence of surface layer atmospheric stability on measurement height at offshore locations. J Wind Eng Ind Aerodyn 131:88–99
Arlot S, Celisse A (2010) A survey of cross-validation procedures for model selection. Stat Surv 4:40–79
Behrens T, Scholten T (2006) A comparison of data-mining techniques in predictive soil mapping. Dev Soil Sci 31:353–617
Bontemps S, Defourny P, Bogaert EV, Arino O, Kalogirou V, Perez JR (2011) GLOBCOVER 2009-Products description and validation report
Breiman L (2001) Random forests. Mach Learn 45:5–32
Breiman L, Friedman J, Stone CJ, Olshen RA (1984) Classification and regression trees. CRC press
Buisson L, Thuiller W, Casajus N, Lek S, Grenouillet G (2010) Uncertainty in ensemble forecasting of species distribution. Glob Change Biol 16:1145–1157
Cortes C, Vapnik V (1995) Support-vector networks. Machine Learn 20:273–297
Danielson JJ, Gesch DB (2011) Global multi-resolution terrain elevation data 2010 (GMTED2010). US Geological Survey
Douak F, Melgani F, Benoudjit N (2013) Kernel ridge regression with active learning for wind speed prediction. Appl Energy 103:328–340
Efron B, Tibshirani RJ (1994) An introduction to the bootstrap. CRC press
Foresti L, Tuia D, Kanevski M, Pozdnoukhov A (2011) Learning wind fields with multiple kernels. Stoch Env Res Risk Assess 25:51–66
Grimm R, Behrens T, Märker M, Elsenbeer H (2008) Soil organic carbon concentrations and stocks on Barro Colorado Island—digital soil mapping using random forests analysis. Geoderma 146:102–113
James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning. Springer
Luo W, Taylor MC, Parker SR (2008) A comparison of spatial interpolation methods to estimate continuous wind speed surfaces using irregularly distributed data from England and Wales. Int J Climatol 28:947–959
Marjanović M, Kovačević M, Bajat B, Voženílek V (2011) Landslide susceptibility assessment using SVM machine learning algorithm. Eng Geol 123:225–234
Meteotest (2016) Windpotentialanalyse für Windatlas.ch Jahresmittelwerte der modellierten Windgeschwindigkeit und Windrichtung. BFE
Mohandes MA, Halawani TO, Rehman S, Hussain AA (2004) Support vector machines for wind speed prediction. Renew Energy 29:939–947
Murphy KP (2012) Machine learning: a probabilistic perspective. MIT press
National Oceanic and Atmospheric Administration (NOAA) (2016) Global surface summary of the day—GSOD
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830
Recknagel F (2001) Applications of machine learning to ecological modelling. Ecol Model 146:303–310
Ruß G, Brenning A (2010) Data mining in precision agriculture: management of spatial information. In: Computational intelligence for knowledge-based systems design. Springer, pp 350–359
Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14:199–222
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodol) 267–288
Veronesi F, Grassi S (2016) Generation and validation of spatial distribution of hourly wind speed time-series using machine learning. In: Journal of Physics: Conference Series. IOP Publishing, p 12001
Veronesi F, Grassi S, Raubal M (2016) Statistical learning approach for wind resource assessment. Renew Sustain Energy Rev 56:836–850
Veronesi F, Grassi S, Raubal M, Hurni L (2015) Statistical learning approach for wind speed distribution mapping: the UK as a case study. In: AGILE 2015. Springer, pp 165–180
Wenger SJ, Olden JD (2012) Assessing transferability of ecological models: an underappreciated aspect of statistical validation. Methods Ecol Evol 3:260–267
Acknowledgements
The authors acknowledge the CTI—Commission for Technology and Innovation (CH), and the SCCER-FURIES—Swiss Competence Center for Energy Research—Future Swiss Electrical Infrastructure, for their financial support to the research activity presented in this paper. The authors would also like to thank NOAA, NASA, ESA and the USGS for providing open data that allowed us to perform this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Veronesi, F., Korfiati, A., Buffat, R., Raubal, M. (2017). Assessing Accuracy and Geographical Transferability of Machine Learning Algorithms for Wind Speed Modelling. In: Bregt, A., Sarjakoski, T., van Lammeren, R., Rip, F. (eds) Societal Geo-innovation. AGILE 2017. Lecture Notes in Geoinformation and Cartography. Springer, Cham. https://doi.org/10.1007/978-3-319-56759-4_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-56759-4_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-56758-7
Online ISBN: 978-3-319-56759-4
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)