×

Learning wind fields with multiple kernels. (English) Zbl 1421.86019

Summary: 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.

MSC:

86A32 Geostatistics
86-04 Software, source code, etc. for problems pertaining to geophysics
68T05 Learning and adaptive systems in artificial intelligence

Software:

PRMLT; SVM; EDA; EnKF; SHOGUN
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Andrienko N, Andrienko G (2006) Exploratory data analysis of spatial and temporal data. Springer, NY · Zbl 1093.62005
[2] Ayotte KW (2008) Computational modelling for wind energy assessment. J Wind Eng Indus Aerodyn 96:1571-1590 · doi:10.1016/j.jweia.2008.02.002
[3] 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 · doi:10.1023/A:1026583021740
[4] 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
[5] Baines PG (1997) Topographic effects in stratified flows. Cambridge University Press, Cambridge · Zbl 0840.76001
[6] 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
[7] Bishop C (2006) Pattern recognition and machine learning. Springer, NY · Zbl 1107.68072
[8] 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
[9] 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 · doi:10.1016/j.renene.2007.08.013
[10] Cressie N (1993) Statistics for spatial data, revised edn. Wiley, NY
[11] Eidsvik KJ (2005) A system for wind power estimation in mountainous terrain. Prediction of Askervein hill data. Wind Energy 8:237-249
[12] 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 · doi:10.1023/B:BOUN.0000030561.25252.9e
[13] Evensen G (2006) Data assimilation: The ensemble Kalman filter. Springer, NY · Zbl 1157.86001
[14] 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 · Zbl 0135.20001
[15] 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 · Zbl 1421.86019
[16] 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 · Zbl 1421.86019
[17] 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)
[18] Freeman WT and Adelson EH (1991) The design and use of steerable filters. IEEE Trans Pattern Anal Mach Intel 13:891-906 · doi:10.1109/34.93808
[19] Freund RM (2004) Solution methods for quadratic optimization. Technical report, Massachusetts Institute of Technology, MA
[20] Gönen M, Alpaydin E (2008) Localized multiple kernel learning. Proceedings of the 25th international conference on machine learning, vol 307. pp 352-359 · doi:10.1145/1390156.1390201
[21] 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
[22] Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46:389-422 · Zbl 0998.68111 · doi:10.1023/A:1012487302797
[23] Guyon I, Gunn S, Nikravesh M, Zadeh LA (eds) (2006) Feature extraction: foundations and applications. Springer, NY · Zbl 1114.68059
[24] Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning, 2nd edn. Springer, NY · Zbl 1273.62005
[25] Haykin S (1999) Neural Networks. Prentice Hall, India · Zbl 0934.68076
[26] Huber PJ (1964) Robust estimation of a location parameter. Ann Math Stat 35(1):73-101 · Zbl 0136.39805 · doi:10.1214/aoms/1177703732
[27] Hughes GF (1968) On the mean accuracy of statistical pattern recognition. IEEE Trans Inf Theory 14(1):55-63 · doi:10.1109/TIT.1968.1054102
[28] Kanevski M (ed) (2008) Advanced mapping of environmental data. ISTE Wiley, NY · Zbl 1207.86002
[29] Kanevski M, Pozdnoukhov A, Timonin V (2009) Machine learning algorithms for spatial data analysis and modelling. EPFL Press, Lausanne
[30] Lanckriet GRG, De Bie T, Cristianini N, Jordan MI, Noble WS (2004) A statistical framework for genomic data fusion. Bioinformatics 20(16):2626-2635 · doi:10.1093/bioinformatics/bth294
[31] 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 · doi:10.1002/we.94
[32] 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 · doi:10.1093/bioinformatics/btl475
[33] 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
[34] Liston GE, Elder KA (2006) Meteorological distribution system for high-resolution terrestrial modeling (microMet). J Hydrometeorol 7:217-234 · doi:10.1175/JHM486.1
[35] Longworth C, Gales MJF (2008) multiple kernel learning for speaker verification. IEEE conference on acoustic, speech and signal processing ICASSP, pp 1581-1584
[36] Martinez WL (2004) Exploratory data analysis with matlab. Chapman & Hall/CRC, London · Zbl 1067.62005
[37] 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
[38] 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 · doi:10.1016/j.jweia.2008.03.012
[39] Petersen EL, Mortensen NG, Landberg L, Hojstrup J, Frank HP (1998) Wind power meteorology. Wind Energy 1:2-22 · doi:10.1002/(SICI)1099-1824(199809)1:1<2::AID-WE15>3.0.CO;2-Y
[40] 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 · Zbl 1407.62346 · doi:10.1007/s00477-007-0162-x
[41] 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
[42] Pozdnoukhov A, Foresti L and Kanevski M (2009) Data-driven topo-climatic mapping with machine learning methods. Nat Haz 3(50):497-518
[43] Rakotomamonjy A, Bach FR, Canu S, Grandvalet Y (2008) Simple MKL. J Mach Learn Res 9:2491-2521 · Zbl 1225.68208
[44] Rätsch G, Sonnenburg S, Schäfer C (2006) Learning interpretable SVMs for biological sequence classification. BMC Bioinformatics 7(Suppl 1):S9 · Zbl 1119.92334 · doi:10.1186/1471-2105-7-S1-S9
[45] Schaffner B, Remund J (eds) (2005) The alpine space wind map: modeling approach. Alpine Windharvest Report Series 7-2. Alpine windharvest partnership network
[46] Schölkopf B (2001) The kernel trick for distances. In: Leen TK, Dietterich TG, and Tresp V (eds) NIPS. MIT Press, Cambridge, pp 301-307
[47] Schölkopf B, Smola A (2002) Learning with Kernels. MIT Press, Cambridge · Zbl 1019.68094
[48] Smola A-J, Schölkopf B (1998) A Tutorial on support vector regression. NeuroCOLT2 technical report series, NC2-TR-1998-030
[49] Sonnenburg S, Schaefer G, Rätsch G, Schölkopf B (2006) Large scale multiple kernel learning. J Mach Learn Res 7:1531-1565 · Zbl 1222.90072
[50] 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
[51] Tuia D, Camps-Valls G, Matasci G, Kanevski M (in press) Learning relevant image features with multiple kernel classification. IEEE Trans Geosci Remote Sens
[52] Vapnik V (1995) The nature of statistical learning theory. Springer, NY · Zbl 0833.62008
[53] Whiteman CD (2000) Mountain meteorology: fundamentals and applications. Oxford University Press, Oxford
[54] Wilson JP, Gallant JC (eds) (2000) Terrain analysis: principles and applications. Wiley, NY
[55] Zien A, Ong CS (2007) Multiclass multiple kernel learning. Proceedings of the 24th international conference on machine learning, vol 227. pp 1191-1198 · doi:10.1145/1273496.1273646
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.