%0 Unpublished work
%T Revealing the dependence structure of scenario-like inputs in numerical environmental simulations using Gaussian Process regression
%+ Bureau de Recherches Géologiques et Minières (BRGM) (BRGM)
%+ Institut National des Sciences Appliquées - Toulouse (INSA Toulouse)
%A Rohmer, Jeremy
%A Roustant, Olivier
%A Lecacheux, Sophie
%A Manceau, Jean-Charles
%Z PSO DRP Incertitudes
%Z Document de travail
%8 2020-12-11
%D 2020
%K Categorical variables
%K Computationally intensive simulator
%K Metamodel
%K Kriging
%K Model selection
%Z Computer Science [cs]/Modeling and Simulation
%Z Environmental Sciences/Environmental and Society
%Z Environmental Sciences/Environmental Engineering
%Z Statistics [stat]/Machine Learning [stat.ML]
%Z Statistics [stat]/Applications [stat.AP]
%Z Sciences of the Universe [physics]/Earth Sciences/Oceanography
%Z Sciences of the Universe [physics]/Earth Sciences/Applied geology
%Z Humanities and Social Sciences/Methods and statisticsPreprints, Working Papers, ...
%X Model uncertainties (related to the structure/form of the model or to the choice of "appropriate" physical laws) are generally integrated in environmental long running numerical simulators via scenario-like variables. By focusing on Gaussian Processes (GP), we show how different categorical covariance functions (exchangeable, ordinal, group, etc.) can bring valuable insights into the inter-dependencies of these scenarios. Supported by two real case applications (cycloneinduced waves and reservoir modelling), we have proposed a cross-validation approach to select the most appropriate covariance function by finding a trade-off between predictability, explainability, and stability of the covariance coefficients. This approach can be effectively used to support (or contradict) some physical assumptions regarding the scenario-like input. Through comparison to tree-based techniques, we show that GP models can be considered a satisfactory compromise when only a few model runs (~100) are available by presenting a high predictability and a concise and graphical way to map the dependence.
%G English
%Z Chaire industrielle OQUAIDO
%2 https://brgm.hal.science/hal-03054381/document
%2 https://brgm.hal.science/hal-03054381/file/Rohmer_etal_EMS.pdf
%L hal-03054381
%U https://brgm.hal.science/hal-03054381
%~ SHS
%~ SDE
%~ BRGM
%~ INSA-TOULOUSE
%~ GIP-BE
%~ FRANTIQ
%~ TDS-MACS
%~ INSA-GROUPE
%~ BRGM-DO