<  Retour au portail Polytechnique Montréal

A machine learning approach for characterizing soil contamination in the presence of physical site discontinuities and aggregated samples

Alyssa Ngu-Oanh Quach, Lucie Tabor, Dany Dumont, Benoit Courcelles et James Alexandre Goulet

Article de revue (2017)

Document en libre accès dans PolyPublie
[img]
Affichage préliminaire
Libre accès au plein texte de ce document
Version finale avant publication
Conditions d'utilisation: Creative Commons: Attribution-Pas d'utilisation commerciale-Pas de modification (CC BY-NC-ND)
Télécharger (1MB)
Afficher le résumé
Cacher le résumé

Abstract

Rehabilitation of contaminated soils in urban areas is in high demand because of the appreciation of land value associated with the increased urbanization. Moreover, there are financial incentives to minimize soil characterization uncertainties. Minimizing uncertainty is achieved by providing models that are better representation of the true site characteristics. In this paper, we propose two new probabilistic formulations compatible with Gaussian Process Regression (GPR) and enabling (1) to model the experimental conditions where contaminant concentration is quantified from aggregated soil samples and (2) to model the effect of physical site discontinuities. The performance of approaches proposed in this paper are compared using a Leave One Out Cross-Validation procedure (LOO-CV). Results indicate that the two new probabilistic formulations proposed outperform the standard Gaussian Process Regression.

Sujet(s): 1000 Génie civil > 1000 Génie civil
Département: Département des génies civil, géologique et des mines
Organismes subventionnaires: Fonds de recherche du Québec - Nature et technologies (FRQNT)
Numéro de subvention: 2017-NC-197235
URL de PolyPublie: https://publications.polymtl.ca/2843/
Titre de la revue: Advanced Engineering Informatics (vol. 33)
Maison d'édition: Elsevier
DOI: 10.1016/j.aei.2017.05.002
URL officielle: https://doi.org/10.1016/j.aei.2017.05.002
Date du dépôt: 15 janv. 2018 13:55
Dernière modification: 26 sept. 2024 11:03
Citer en APA 7: Quach, A. N.-O., Tabor, L., Dumont, D., Courcelles, B., & Goulet, J. A. (2017). A machine learning approach for characterizing soil contamination in the presence of physical site discontinuities and aggregated samples. Advanced Engineering Informatics, 33, 60-67. https://doi.org/10.1016/j.aei.2017.05.002

Statistiques

Total des téléchargements à partir de PolyPublie

Téléchargements par année

Provenance des téléchargements

Dimensions

Actions réservées au personnel

Afficher document Afficher document