Tackling random fields non-linearities with unsupervised clustering of polynomial chaos expansion in latent space: application to global sensitivity analysis of river flooding
Open Access
- 2 August 2021
- journal article
- research article
- Published by Springer Nature in Stochastic Environmental Research and Risk Assessment
- Vol. 36 (3) , 693-718
Abstract
A surrogate model is developed to accurately approximate a two-dimensional hydrodynamics numerical solver in order to conduct a reduced-cost variance-based global sensitivity analysis of the hydraulic state. The impact of uncertainties in river bottom friction and boundary conditions on the simulated water depth is analyzed for quasi-unsteady flows. An autoencoder technique adapted to non-linear variable dimension reduction is used to reduce the multi-dimensional model output so that the formulation of the surrogate remains computationally parsimonious. In addition, following the divide-and-conquer principle, a mixture of local polynomial chaos expansions is proposed to deal with non-linearity in the hydraulic state with respect to uncertain inputs. Machine learning techniques are used to automatically partition the input space into clusters that are not affected by non-linearities and support accurate surrogates. This combined strategy is applied to a reach of the Garonne River where river and floodplains dynamics are simulated by the numerical solver Telemac-2D. The merits of this strategy are highlighted when the flood front reaches regions where the topography features a strong gradient and where, consequently, strong non-linearities occur between the water depth and friction as well as hydrologic input forcing. By applying this strategy, the $$Q_2$$ metric improves by 90% compared to a classical polynomial chaos expansion surrogate, resulting in a much more reliable sensitivity analysis. This is particularly important in floodplain areas where human and economic activities are at stake.
Keywords
Funding Information
- CERFACS
- Occitanie region
- French National Program LEFE/INSU
This publication has 83 references indexed in Scilit:
- Review of surrogate modeling in water resourcesWater Resources Research, 2012
- Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity indexComputer Physics Communications, 2010
- A triangular spectral/hp discontinuous Galerkin method for modelling 2D shallow water equationsInternational Journal for Numerical Methods in Fluids, 2004
- The global k-means clustering algorithmPattern Recognition, 2003
- Sensitivity measures,anova-like Techniques and the use of bootstrapJournal of Statistical Computation and Simulation, 1997
- Support-vector networksMachine Learning, 1995
- Backpropagation and stochastic gradient descent methodNeurocomputing, 1993
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- River flow forecasting through conceptual models part I — A discussion of principlesJournal of Hydrology, 1970
- Reduction of Dimensionality, Dynamic Programming, and Control ProcessesJournal of Basic Engineering, 1961