Alyssa Quach's Research Page

  /main page/research axes/Alyssa Quach

Former Position Student | 2015 - 2017



EXP Global

Montréal, CANADA

Education, Civil Engineering | 2015-2017
   Polytechnique Montreal

   Advisor: James-A Goulet, Civil Engineering | 2011 - 2015

        Polytechnique Montreal, Canada



Title: A Machine Learning Approach for Characterizing Soil Contamination in the Presence of Physical Site Discontinuities and Aggregated Samples

Summary: 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 research, we propose two new probabilistic formulations compatible with Gaussian Process Regression 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).  Each of the two new probabilistic formulations proposed outperformed the standard Gaussian Process Regression (GPR) approach and the combination of the two new formulations outperforms the usage of each one separately.

The Figure below present an example of soil contamination caracterization obtained using the method developped in this research project.


[2017]  A machine learning approach for characterizing soil contamination in the presence of physical site

           discontinuities and aggregated samples

            Quach, A., Tabor, L., Dumont, D., Courcelles, B., and Goulet, J.-A..

            Advanced Engineering Informatics., vol.66, pp. 60-67.

            [PDF] [EndNote] [BibTeX] [DOI link]