Evaluation of a Depth-Based Multivariate K-Nearest Neighbor Resampling Method with Stormwater Quality Data.

Lee, Taesam; Ouarda, Taha B. M. J.; Chebana, Fateh et Park, Daeryong (2014). Evaluation of a Depth-Based Multivariate K-Nearest Neighbor Resampling Method with Stormwater Quality Data. Mathematical Problems in Engineering , vol. 2014 . p. 404198. DOI: 10.1155/2014/404198.

Prévisualisation

PDF Télécharger (4MB) | Prévisualisation

Résumé

A nonparametric simulation model (K-nearest neighbor resampling, KNNR) for water quality analysis involving geographic information is suggested to overcome the drawbacks of parametric models. Geographic information is, however, not appropriately handled in the KNNR nonparametricmodel. In the current study, we introduce a novel statistical notion, called a “depth function,” in the classical KNNR model to appropriately manipulate geographic information in simulating stormwater quality. An application is presented for a case study of the total suspended solids throughout the entire United States. The stormwater total suspended solids concentration data indicated that the proposedmodel significantly improves the simulation performance compared with the existing KNNR model.

Type de document:	Article
Mots-clés libres:	geographic information; nearest neighbors; non-parametric model; resampling method; simulation performance; stormwater quality; total suspended solids; water quality analysis
Centre:	Centre Eau Terre Environnement
Date de dépôt:	18 avr. 2018 13:18
Dernière modification:	27 nov. 2019 14:50
URI:	https://espace.inrs.ca/id/eprint/3769

Gestion Actions (Identification requise)

Modifier la notice