NUI Maynooth

NUIM ePrints and eTheses Archive

NUIM Library

Learning wind fields with multiple kernels

Foresti , Loris and Tuia, Devis and Kanevski, Mikhail and Pozdnoukhov, Alexei (2011) Learning wind fields with multiple kernels. Stochastic Environmental Research and Risk Assessment, 25 (1). pp. 51-66. ISSN 1436-3240

[img] Download (1MB)

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.

Item Type: Article
Additional Information: The final and definitive version of this article was published in Stochastic Environmental Research and Risk Assessment Vol.25 No.1(2011) and is available at DOI: 10.1007/s00477-010-0405-0
Keywords: Multiple kernel learning; Support vector regression; Feature selection; Wind resource estimation; Topographic features indices extraction;
Subjects: Science & Engineering > National Center for Geocomputation, NCG
Item ID: 3929
Depositing User: Dr Alexei Pozdnoukhov
Date Deposited: 04 Oct 2012 08:49
Journal or Publication Title: Stochastic Environmental Research and Risk Assessment
Publisher: Springer Verlag
Refereed: Yes
URI:

Repository Staff Only(login required)

View Item Item control page

Document Downloads

More statistics for this item...