OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Physically interpretable machine learning algorithm on multidimensional non-linear fields

Mouradi, Rem-Sophia and Goeury, Cédric and Thual, Olivier and Zaoui, Fabrice and Tassi, Pablo Physically interpretable machine learning algorithm on multidimensional non-linear fields. (2021) Journal of Computational Physics, 428. 110074. ISSN 0021-9991

[img]
Preview
(Document in English)

PDF (Publisher's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
2MB

Official URL: https://doi.org/10.1016/j.jcp.2020.110074

Abstract

In an ever-increasing interest for Machine Learning (ML) and a favorable data development context, we here propose an original methodology for data-based prediction of two-dimensional physical fields. Polynomial Chaos Expansion (PCE), widely used in the Uncertainty Quantification community (UQ), has long been employed as a robust representation for probabilistic input-to-output mapping. It has been recently tested in a pure ML context, and shown to be as powerful as classical ML techniques for point-wise prediction. Some advantages are inherent to the method, such as its explicitness and adaptability to small training sets, in addition to the associated probabilistic framework. Simultaneously, Dimensionality Reduction (DR) techniques are increasingly used for pattern recognition and data compression and have gained interest due to improved data quality. In this study, the interest of Proper Orthogonal Decomposition (POD) for the construction of a statistical predictive model is demonstrated. Both POD and PCE have amply proved their worth in their respective frameworks. The goal of the present paper was to combine them for a field-measurement-based forecasting. The described steps are also useful to analyze the data. Some challenging issues encountered when using multidimensional field measurements are addressed, for example when dealing with few data. The POD-PCE coupling methodology is presented, with particular focus on input data characteristics and training-set choice. A simple methodology for evaluating the importance of each physical parameter is proposed for the PCE model and extended to the POD-PCE coupling.

Item Type:Article
Additional Information:Thanks to the editor Elsevier. The article is avalable at : https://www.sciencedirect.com/. This is an open access article under the Creative Commons Attribu-tion (CC BY 4.0) license, which permits others to distribute, remix,adapt and build upon this work, for commercial use, provided theoriginal work is properly cited.
HAL Id:hal-03181089
Audience (journal):International peer-reviewed journal
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Other partners > EDF (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Other partners > Centre d'études et d'expertise sur les risques, l'environnement, la mobilité et l'aménagement - CEREMA (FRANCE)
Other partners > Centre Européen de Recherche et Formation Avancées en Calcul Scientifique - CERFACS (FRANCE)
Other partners > Ecole des Ponts ParisTech (FRANCE)
Laboratory name:
Statistics:download
Deposited On:18 Mar 2021 12:07

Repository Staff Only: item control page