AGILE 2015 pp 165-180 | Cite as

Statistical Learning Approach for Wind Speed Distribution Mapping: The UK as a Case Study

  • Fabio VeronesiEmail author
  • Stefano Grassi
  • Martin Raubal
  • Lorenz Hurni
Part of the Lecture Notes in Geoinformation and Cartography book series (LNGC)


Wind resource assessment is fundamental when selecting a site for wind energy projects. Wind speed is influenced by a plethora of environmental factors and understanding its spatial variability is key for determining the economic viability of a site. Deterministic estimation methods, which are based on physics, represent the industry standard in wind-speed mapping. Over the years, these methods have proven capable of estimating wind speed with a relatively high accuracy. However measuring stations, which provide the starting data for all wind speed estimations, are often located at a distance from each other, in some cases, tens of kilometres or more. This adds an unavoidable level of uncertainty to the estimates, which deterministic methods fail to take into account. For this reason, even though there are ways of determining the overall uncertainty of the estimation, e.g. cross-validation, deterministic methods do not provide means of assessing the site-specific uncertainty. This paper introduces a statistical method for estimating wind speed, based on spatial statistics. In particular, we present a statistical learning approach, based on ensembles of regression trees, to estimate both the wind distribution in specific locations and to assess the site-specific uncertainty.


Wind speed Statistical learning Geostatistics Weibull distribution Random forest 



The authors would like to thank the UK Meteorological Office for providing the wind speed data for this research and some of the covariates. Other data providers we would like to thank are: NASA for the Aster DTM and the EU for the land-cover raster.


  1. Agarwal, S. K., & Kalla, S. L. (1996). A generalized gamma distribution and its application in reliability. Communications in Statistics. Theory and Methods, 25, 201–210.CrossRefGoogle Scholar
  2. Akpinar, E. K., & Akpinar, S. (2005). An assessment on seasonal analysis of wind energy characteristics and wind turbine characteristics. Energy Conversion and Management, 46, 1848–1867.CrossRefGoogle Scholar
  3. Beaucage, P., Brower, M. C., & Tensen, J. (2014). Evaluation of four numerical wind flow models for wind resource mapping. Wind Energy, 17(2), 197–208.CrossRefGoogle Scholar
  4. Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.CrossRefGoogle Scholar
  5. Cellura, M., Cirrincione, G., Marvuglia, A., et al. (2008a). Wind speed spatial estimation for energy planning in Sicily: Introduction and statistical analysis. Renewable Energy, 33, 1237–1250.CrossRefGoogle Scholar
  6. Cellura, M., Cirrincione, G., Marvuglia, A., et al. (2008b). Wind speed spatial estimation for energy planning in Sicily: A neural kriging application. Renewable Energy, 33, 1251–1266.CrossRefGoogle Scholar
  7. Center N.L.P.D.A.A. (2011). ASTER L1B. USGS/Earth Resources Observation and Science (EROS) Center, Sioux Falls, South Dakota.Google Scholar
  8. Chan, J. C. W., & Paelinckx, D. (2008). Evaluation of random forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery. Remote Sensing of Environment, 112, 2999–3011.CrossRefGoogle Scholar
  9. Conrad, O. (2007). SAGA—Entwurf, Funktionsumfang und Anwendung eines Systems für Automatisierte Geowissenschaftliche Analysen. Mathematisch-Naturwissenschaftlichen Fakultäten vol. Ph.D. University of Göttingen.Google Scholar
  10. Cutler, D. R., Edwards, T. C, Jr, Beard, K. H., et al. (2007). Random forests for classification in ecology. Ecology, 88, 2783–2792.CrossRefGoogle Scholar
  11. Foresti, L., Tuia, D., Kanevski, M., & Pozdnoukhov, A. (2011). Learning wind fields with multiple kernels. Stochastic Environmental Research and Risk Assessment, 25(1), 51–66.CrossRefGoogle Scholar
  12. Gass, V., Strauss, F., Schmidt, J., et al. (2011). Assessing the effect of wind power uncertainty on profitability. Renewable and Sustainable Energy Reviews, 15, 2677–2683.CrossRefGoogle Scholar
  13. Gasset, N., Landry, M., & Gagnon, Y. (2012). A comparison of wind flow models for wind resource assessment in wind energy applications. Energies, 5(11), 4288–4322.CrossRefGoogle Scholar
  14. Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006). Random forests for land cover classification. Pattern Recognition Letters, 27, 294–300.CrossRefGoogle Scholar
  15. Grassi, S., Chokani, N., & Abhari, R. (2012). Large scale technical and economic assessment of wind energy potential with a GIS tool: Case study Iowa. Energy Policy, 45, 58–73.CrossRefGoogle Scholar
  16. Grimm, R., Behrens, T., Märker, M., et al. (2008). Soil organic carbon concentrations and stocks on Barro Colorado Island—Digital soil mapping using random forests analysis. Geoderma, 146, 102–113.CrossRefGoogle Scholar
  17. Gsänger, S., & Pitteloud, J. D. (2012). World wind energy association WWEA.Google Scholar
  18. Hansen, M., Dubayah, R., & Defries, R. (1996). Classification trees: an alternative to traditional land cover classifiers. International Journal of Remote Sensing, 17, 1075–1081.CrossRefGoogle Scholar
  19. Hoaglin, D. C., Mosteller, F., & Tukey, J. W. (1983). Understanding robust and exploratory data analysis (Vol. 3). New York: Wiley.Google Scholar
  20. Huang, C., Davis, L. S., & Townshend, J. R. G. (2002). An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23(4), 725–749.CrossRefGoogle Scholar
  21. Jackson, P. S., & Hunt, J. C. R. (1975). Turbulent wind flow over a low hill. Quarterly Journal of the Royal Meteorological Society, 101(430), 929–955.CrossRefGoogle Scholar
  22. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning. New York: Springer.CrossRefGoogle Scholar
  23. Jenkins, G. J., Perry, M. C., & Prior, M. J. (2008). The climate of the United Kingdom and recent trends. Exeter, UK: Met Office Hadley Centre.Google Scholar
  24. Kotsiantis, S. B., Zaharakis, I., & Pintelas, P. (2007). Supervised machine learning: A review of classification techniques.Google Scholar
  25. Kwon, S. D. (2010). Uncertainty analysis of wind energy potential assessment. Applied Energy, 87, 856–865.CrossRefGoogle Scholar
  26. Landberg, L., Myllerup, L., Rathmann, O., et al. (2003). Wind resource estimation—An overview. Wind Energy, 6, 261–271.CrossRefGoogle Scholar
  27. Luo, W., Taylor, M. C., & Parker, S. R. (2008). A comparison of spatial interpolation methods to estimate continuous wind speed surfaces using irregularly distributed data from England and Wales. International Journal of Climatology, 28, 947–959.CrossRefGoogle Scholar
  28. Manwell, J. F., McGowan, J. G., & Rogers, A. L. (2009). Wind characteristics and resources. In Wind energy explained—Theory, design and application (2nd ed., pp. 43–45). New York: Wiley.Google Scholar
  29. Meng, Q., Liu, Z., & Borders, B. E. (2013). Assessment of regression kriging for spatial interpolation–comparisons of seven GIS interpolation methods. Cartography and Geographic Information Science, 40, 28–39.CrossRefGoogle Scholar
  30. Met Office. (2012). Met office integrated data archive system (MIDAS) land and marine surface stations data (1853-current). NCAS British Atmospheric Data Centre:
  31. MM5 Community Model (2015).
  32. Munteanu, I., Cutululis, N. A., Bratcu, A. I., et al. (2008). Optimal control of wind energy systems: Towards a global approach. New York: Springer.Google Scholar
  33. Pinson, P. (2006). Estimation of the uncertainty in wind power forecasting. Thesis/dissertation.Google Scholar
  34. Ray, M. L., Rogers, A. L., & McGowan, J. G. (2006) Analysis of wind shear models and trends in different terrain. In: Proceedings American Wind Energy Association Windpower.Google Scholar
  35. REN21. (2012). Renewables 2012 global status report.Google Scholar
  36. Rogers, A. L., Manwell, J. F., & Ellis, A. F. (2005) Wind shear over forested areas. In Proceedings of the 43rd American Institute of Aeronautics and Astronautics Aerospace, Science Meeting.Google Scholar
  37. Schmidli, J., Billings, B., Chow, F. K., et al. (2010). Intercomparison of mesoscale model simulations of the daytime valley wind system. Monthly Weather Review, 139, 1389–1409.CrossRefGoogle Scholar
  38. Snel, H. (1998). Review of the present status of rotor aerodynamics. Wind Energy, 1(1), 46–69.CrossRefGoogle Scholar
  39. Susumu, S., Ohsawa, T., & Yatsu, K. (2009). A study on the ability of mesoscale model MM5 for offshore wind resource assessment in Japanese coastal waters. In European Wind Energy Conference EWEC.Google Scholar
  40. VanLuvanee, D., et al. (2009). Comparison of WAsP, MS-Micro/3, CFD, NWP, and analytical methods for estimating site-wide wind speeds. In: Presentation from AWEA wind, 2009.Google Scholar
  41. WAsP (2015).
  42. Wiesmeier, M., Barthold, F., Blank, B., et al. (2011). Digital mapping of soil organic matter stocks using random forest modeling in a semi-arid steppe ecosystem. Plant and Soil, 340, 7–24.CrossRefGoogle Scholar
  43. Yim, S. H. L., Fung, J. C. H., Lau, A. K. H., et al. (2007). Developing a high-resolution wind map for a complex terrain with a coupled MM5/CALMET system. Journal of Geophysical Research: Atmospheres, 112(D5), 2156–2202.Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Fabio Veronesi
    • 1
    Email author
  • Stefano Grassi
    • 1
  • Martin Raubal
    • 1
  • Lorenz Hurni
    • 1
  1. 1.Institute of Cartography and GeoinformationZurichSwitzerland

Personalised recommendations