Dépôt numérique

Comparative study of feature selection methods for wind speed estimation at ungauged locations.


Téléchargements par mois depuis la dernière année

Plus de statistiques...

Houndekindo, Freddy ORCID logoORCID: https://orcid.org/0000-0002-8702-6873 et Ouarda, Taha B. M. J. ORCID logoORCID: https://orcid.org/0000-0002-0969-063X (2023). Comparative study of feature selection methods for wind speed estimation at ungauged locations. Energy Conversion and Management , vol. 291 . p. 117324. DOI: 10.1016/j.enconman.2023.117324.

[thumbnail of P4333.pdf]
Télécharger (1MB) | Prévisualisation


Wind speed estimation at ungauged locations is one of the preliminary steps for wind resource assessment. With the availability of high-resolution Digital Elevation Models (DEM) and remote sensing data, the number of potential wind speed predictors has grown substantially. The adequate spatial scale of these predictors is unknown a priori, leading to the use of multiple spatial scales of predictors in wind speed estimation models. Implementing a feature selection method as a pre-processing step of the analysis is necessary to avoid overfitting and the resulting potential model underperformance. This paper evaluated six feature selection methods (forward stepwise regression, Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net, maximum relevance minimum redundancy (MRMR), Genetic algorithm, and recursive feature elimination using support vector regression) for the estimation of different wind speed quantiles across Canada. The selected features were used to fit a regression-kriging model, and the importance of the predictors was evaluated with their associated regression coefficients. The results of the study showed that LASSO and MRMR are the most efficient algorithms with the least number of parameters to tune and good generalization performance. The study found that some predictors were more important for specific exceedance probabilities. The most important predictors were the distance from the coast and surface roughness length, regardless of exceedance probability.

Type de document: Article
Mots-clés libres: exceedance probability; feature selection; machine learning; topographic feature; ungauged location; wind speed
Centre: Centre Eau Terre Environnement
Date de dépôt: 02 nov. 2023 14:33
Dernière modification: 02 nov. 2023 14:33
URI: https://espace.inrs.ca/id/eprint/13720

Gestion Actions (Identification requise)

Modifier la notice Modifier la notice