GEOSCAN, résultats de la recherche

Menu GEOSCAN


TitrePredicting hydrofacies and hydraulic conductivity from direct-push data using a data-driven relevance vector machine approach: motivations, algorithms and application
AuteurParadis, D; Lefebvre, R; Gloaguen, E; Rivera, A
SourceWater Resources Research vol. 51, 2015 p. 481-505, https://doi.org/10.1002/2014WR015452 (Accès ouvert)
Année2015
Séries alt.Secteur des sciences de la Terre, Contribution externe 20130456
ÉditeurWiley-Blackwell
Documentpublication en série
Lang.anglais
DOIhttps://doi.org/10.1002/2014WR015452
Mediapapier; en ligne; numérique
Formatspdf
ProvinceQuébec
SNRC21L/11
Lat/Long OENS -71.5000 -71.0000 46.7500 46.5000
Sujetsconductivité hydraulique; écoulement de la nappe d'eau souterraine; pénétromètres; résistivité électrique; aquifères; puits d'eau; humidité du sol; pressions interstitielles; hydrogéologie; géophysique; géochimie
Illustrationsgeological sketch maps; graphs; tables; histograms; diagrams; plots
Diffusé2015 01 22
Résumé(disponible en anglais seulement)
The spatial heterogeneity of hydraulic conductivity (K) exerts a major control on groundwater flow and solute transport. The heterogeneous spatial distribution of K can be imaged using indirect geophysical data as long as reliable relations exist to link geophysical data to K. This paper presents a nonparametric learning machine approach to predict aquifer K from cone penetrometer tests (CPT) coupled with a soil moisture and resistivity probe (SMR) using relevance vector machines (RVMs). The learning machine approach is demonstrated with an application to a heterogeneous unconsolidated littoral aquifer in a 12 km2 subwatershed, where relations between K and multiparameters CPT/SMR soundings appear complex. Our approach involved fuzzy clustering to define hydrofacies (HF) on the basis of CPT/SMR and K data prior to the training of RVMs for HFs recognition and K prediction on the basis of CPT/SMR data alone. The learning machine was built from a colocated training data set representative of the study area that includes K data from slug tests and CPT/SMR data up-scaled at a common vertical resolution of 15 cm with K data. After training, the predictive capabilities of the learning machine were assessed through cross validation with data withheld from the training data set and with K data from flowmeter tests not used during the training process. Results show that HF and K predictions from the learning machine are consistent with hydraulic tests. The combined use of CPT/SMR data and RVM-based learning machine proved to be powerful and efficient for the characterization of high-resolution K heterogeneity for unconsolidated aquifers.
Résumé(Résumé en langage clair et simple, non publié)
L'hétérogéniété de la conductivité hydraulique (K) exerce un contrôle important sur l'écoulement de l'eau souterraine et le transport des contaminants. Cet article propose une nouvelle méthode pour représenter la distribution spatiale des valeurs de K à partir de mesures géophysiques et d'algorithmes de distribution spatiale. L'utilisation conjointe de ces deux méthodes (CPT/SMR et RVM learning machine), semble être une façon efficace et efficient pour représenter les valeurs de conductivité hydraulique des aquifères granulaires.
GEOSCAN ID293615