Skip to main content
SpringerLink
Log in

Learning wind fields with multiple kernels

  • Original Paper
  • Published:
Stochastic Environmental Research and Risk Assessment Aims and scope Submit manuscript

Abstract

This paper presents multiple kernel learning (MKL) regression as an exploratory spatial data analysis and modelling tool. The MKL approach is introduced as an extension of support vector regression, where MKL uses dedicated kernels to divide a given task into sub-problems and to treat them separately in an effective way. It provides better interpretability to non-linear robust kernel regression at the cost of a more complex numerical optimization. In particular, we investigate the use of MKL as a tool that allows us to avoid using ad-hoc topographic indices as covariables in statistical models in complex terrains. Instead, MKL learns these relationships from the data in a non-parametric fashion. A study on data simulated from real terrain features confirms the ability of MKL to enhance the interpretability of data-driven models and to aid feature selection without degrading predictive performances. Here we examine the stability of the MKL algorithm with respect to the number of training data samples and to the presence of noise. The results of a real case study are also presented, where MKL is able to exploit a large set of terrain features computed at multiple spatial scales, when predicting mean wind speed in an Alpine region.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Notes

  1. http://asi.insa-rouen.fr/enseignants/∼arakotom/code/mklindex.html.

  2. We refer to spatial coordinates when using uppercase X and Y; on the other hand, x is the input vector and y is the output.

  3. More informations can be found on: The Swiss Wind Power Data Website, http://www.wind-data.ch/index.php.

References

  • Andrienko N, Andrienko G (2006) Exploratory data analysis of spatial and temporal data. Springer, NY

  • Ayotte KW (2008) Computational modelling for wind energy assessment. J Wind Eng Indus Aerodyn 96:1571–1590

    Article  Google Scholar 

  • Ayotte KW, Davy RJ, Coppin PA (2001) A simple temporal and spatial analysis of flow in complex terrain in the context of wind energy modeling. Boundary-Layer Meteorol 98:275–295

    Article  Google Scholar 

  • Bach FR, Lanckriet GRG, Jordan MI (2004) Multiple kernel learning, conic duality and the SMO algorithm. In: Proceedings of the 21th international conference on machine learning 69

  • Baines PG (1997) Topographic effects in stratified flows. Cambridge University Press, Cambridge

  • Beccali M, Cirrincione G, Marvuglia A, Serporta C (In press) Estimation of wind velocity over a complex terrain using the generalized mapping regressor. Applied Energy

  • Bishop C (2006) Pattern recognition and machine learning. Springer, NY

  • Canu S, Grandvalet Y, Guigue V, and Rakotomamonjy A (2005) SVM and kernel methods matlab toolbox. Perception Systèmes et Information, INSA de Rouen, Rouen, France

  • Cellura M, Cirrincione G, Marvuglia A, Miraoui A (2008) Wind speed spatial estimation for energy planning in Sicily: a neural kriging application. Renew Energy 33:1251–1266

    Article  Google Scholar 

  • Cressie N (1993) Statistics for spatial data, revised edn. Wiley, NY

  • Eidsvik KJ (2005) A system for wind power estimation in mountainous terrain. Prediction of Askervein hill data. Wind Energy 8:237–249

    Google Scholar 

  • Eidsvik KJ, Holstad A, Lie I, Utnes T (2004) A prediction system for local wind variations in mountainous terrain. Boundary-Layer Meteorology 112:557–586

    Article  Google Scholar 

  • Evensen G (2006) Data assimilation: The ensemble Kalman filter. Springer, NY

  • Faure P, Huard P (1965) Résolution de programmes mathématiques à fonction non linéaire par la méthode du gradient réduit, Revue Française de Recherche Opérationnelle 36

  • Foresti L, Pozdnoukhov A, Tuia D and Kanevski M (In press) Extreme precipitation modelling using geostatistics and machine learning algorithms. Proceedings of the 7th international conference on geostatistics for environmental applications

  • Foresti L, Tuia D, Pozdnoukhov A, Kanevski M (2009) Multiple kernel learning of environmental data. Case study: analysis and mapping of wind fields. Proceedings of the 19th international conference on artificial neural networks, Part II, pp 933–943

  • Franck HP, Rathmann O, Mortensen NG, Landberg L (2001) The numerical wind atlas—the KAMM/WAsP method. Risoe National Laboratory publications, Danemark Risoe-R-1252(EN)

  • Freeman WT and Adelson EH (1991) The design and use of steerable filters. IEEE Trans Pattern Anal Mach Intel 13:891–906

    Article  Google Scholar 

  • Freund RM (2004) Solution methods for quadratic optimization. Technical report, Massachusetts Institute of Technology, MA

  • Gönen M, Alpaydin E (2008) Localized multiple kernel learning. Proceedings of the 25th international conference on machine learning, vol 307. pp 352–359

    Article  Google Scholar 

  • Gravdahl AR (1998) Meso scale modeling with a reynolds averaged navier-stokes solver: assessment of wind resources along the Norwegian coast. 31th IEA experts meeting. State of the Art on Wind Resource Estimation

  • Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46:389–422

    Article  Google Scholar 

  • Guyon I, Gunn S, Nikravesh M, Zadeh LA (eds) (2006) Feature extraction: foundations and applications. Springer, NY

  • Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning, 2nd edn. Springer, NY

  • Haykin S (1999) Neural Networks. Prentice Hall, India

  • Huber PJ (1964) Robust estimation of a location parameter. Ann Math Stat 35(1):73–101

    Article  Google Scholar 

  • Hughes GF (1968) On the mean accuracy of statistical pattern recognition. IEEE Trans Inf Theory 14(1):55–63

    Article  Google Scholar 

  • Kanevski M (ed) (2008) Advanced mapping of environmental data. ISTE Wiley, NY

  • Kanevski M, Pozdnoukhov A, Timonin V (2009) Machine learning algorithms for spatial data analysis and modelling. EPFL Press, Lausanne

  • Lanckriet GRG, De Bie T, Cristianini N, Jordan MI, Noble WS (2004) A statistical framework for genomic data fusion. Bioinformatics 20(16):2626–2635

    Article  CAS  Google Scholar 

  • Landberg L, Myllerup L, Rathmann O, Petersen EL, Jorgensen BH, Badger J, Mortensen NG (2003) Wind resource estimation-an overview. Wind Energy 6:261–271

    Article  Google Scholar 

  • Lewis DP, Jebara T, Noble WS (2006) Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure. Bioinformatics 22:2753–2760

    Article  CAS  Google Scholar 

  • Lindsay JB, Rothwell J (2008) Modelling channeling and deflection of wind by topography. In: Zhou Q, Lees B (eds) Advances in digital terrain analysis. Springer, NY, pp 383–406

  • Liston GE, Elder KA (2006) Meteorological distribution system for high-resolution terrestrial modeling (microMet). J Hydrometeorol 7:217–234

    Article  Google Scholar 

  • Longworth C, Gales MJF (2008) multiple kernel learning for speaker verification. IEEE conference on acoustic, speech and signal processing ICASSP, pp 1581–1584

  • Martinez WL (2004) Exploratory data analysis with matlab. Chapman & Hall/CRC, London

  • Mercer J (1905) Functions of positive and negative type and their connection with the theory of integral equations. Phil Trans R Soc CCIX:215–228

    Google Scholar 

  • Palma JMLM, Castro FA, Ribeiro LF, Rodrigues AH, Pinto AP (2008) Linear and nonlinear models in wind resource assessment and wind turbine micro-siting in complex terrain. J Eng Indus Aerodyn 96:2308–2326

    Article  Google Scholar 

  • Petersen EL, Mortensen NG, Landberg L, Hojstrup J, Frank HP (1998) Wind power meteorology. Wind Energy 1:2–22

    Article  Google Scholar 

  • Pozdnoukhov A, Kanevski M (2008) Multi-scale support vector algorithms for hot spot detection and modelling. Stoch Environ Res Risk Assess 22(5):647–660

    Article  Google Scholar 

  • Pozdnoukhov A, Kanevski M, Timonin V (2007) Prediction of wind power density using machine learning algorithms. Proceedings of the 12th annual conference of international association for mathematical Geology

  • Pozdnoukhov A, Foresti L and Kanevski M (2009) Data-driven topo-climatic mapping with machine learning methods. Nat Haz 3(50):497–518

    Google Scholar 

  • Rakotomamonjy A, Bach FR, Canu S, Grandvalet Y (2008) Simple MKL. J Mach Learn Res 9:2491–2521

    Google Scholar 

  • Rätsch G, Sonnenburg S, Schäfer C (2006) Learning interpretable SVMs for biological sequence classification. BMC Bioinformatics 7(Suppl 1):S9

    Article  CAS  Google Scholar 

  • Schaffner B, Remund J (eds) (2005) The alpine space wind map: modeling approach. Alpine Windharvest Report Series 7–2. Alpine windharvest partnership network

  • Schölkopf B (2001) The kernel trick for distances. In: Leen TK, Dietterich TG, and Tresp V (eds) NIPS. MIT Press, Cambridge, pp 301–307

  • Schölkopf B, Smola A (2002) Learning with Kernels. MIT Press, Cambridge

  • Smola A-J, Schölkopf B (1998) A Tutorial on support vector regression. NeuroCOLT2 technical report series, NC2-TR-1998-030

  • Sonnenburg S, Schaefer G, Rätsch G, Schölkopf B (2006) Large scale multiple kernel learning. J Mach Learn Res 7:1531–1565

    Google Scholar 

  • Tuia D, Kanevski M (2008) Environmental monitoring network characterization and clustering. In: Kanevski (ed) Advanced mapping of environmental data. ISTE Wiley, NY, pp 19–47

  • Tuia D, Camps-Valls G, Matasci G, Kanevski M (in press) Learning relevant image features with multiple kernel classification. IEEE Trans Geosci Remote Sens

  • Vapnik V (1995) The nature of statistical learning theory. Springer, NY

  • Whiteman CD (2000) Mountain meteorology: fundamentals and applications. Oxford University Press, Oxford

  • Wilson JP, Gallant JC (eds) (2000) Terrain analysis: principles and applications. Wiley, NY

  • Zien A, Ong CS (2007) Multiclass multiple kernel learning. Proceedings of the 24th international conference on machine learning, vol 227. pp 1191–1198

    Article  Google Scholar 

Download references

Acknowledgements

The research is funded in part by the Swiss National Science Foundation projects “GeoKernels: kernel-based methods for geo- and environmental sciences (Phase II)” (No 200020-121835/1) and “Structured learning for remote sensing data analysis” (PBLAP2-127713/1). A. Pozdnoukhov acknowledges the support of Science Foundation Ireland under the National Development Plan, particularly through Stokes Award and Strategic Research Cluster grant (07/SRC/I1168). The authors would like to acknowledge Prof. S. Canu and Prof. A. Rakotomamonjy for the useful discussion and interesting comments.

Author information

Authors and Affiliations

  1. Institute of Geomatics and Analysis of Risk, University of Lausanne, Amphipôle Building, 1015, Lausanne, Switzerland

    Loris Foresti, Devis Tuia & Mikhail Kanevski

  2. National Centre for Geocomputation, National University of Ireland, John Hume Building, Maynooth, Ireland

    Alexei Pozdnoukhov

Authors
  1. Loris Foresti
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Devis Tuia
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mikhail Kanevski
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alexei Pozdnoukhov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Loris Foresti or Alexei Pozdnoukhov.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Foresti, L., Tuia, D., Kanevski, M. et al. Learning wind fields with multiple kernels. Stoch Environ Res Risk Assess 25, 51–66 (2011). https://doi.org/10.1007/s00477-010-0405-0

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00477-010-0405-0

Keywords

Search

Navigation