Alejandro Ribés
Research Subjects
Research Interests
Alejandro Ribés has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Bertrand Iooss
EDF R&D
2 shared publications - Bruno Raffin
Univ. Grenoble Alpes Inria CNRS Grenoble INP LIG Grenoble France
2 shared publications - Joachim Pouderoux
Kitware 6 Cours André Philip 69100 Villeurbanne France
2 shared publications - Yvan Fournier
EDF R&D
2 shared publications Anthony Geay
EDF Lab Paris-Saclay
1 shared publication- Benjamin Lorendeau
EDF R&D
1 shared publication
Latest Publications
- Open Access
Simulation-Based Parallel Training
Numerical simulations are ubiquitous in science and engineering. Machine learning for science investigates how artificial neural architectures can learn from these simulations to speed up scientific discovery and engineering processes. Most of these architectures are trained in a supervised manner. They require tremendous amounts of data from simulations that are slow to generate and memory greedy. In this article, we present our ongoing work to design a training framework that alleviates those bottlenecks. It generates data in parallel with the training process. Such simultaneity induces a bias in the data available during the training. We present a strategy to mitigate this bias with a memory buffer. We test our framework on the multi-parametric Lorenz's attractor. We show the benefit of our framework compared to offline training and the success of our data bias mitigation strategy to capture the complex chaotic dynamics of the system.
Open AccessSimulation-Based Parallel Training
Numerical simulations are ubiquitous in science and engineering. Machine learning for science investigates how artificial neural architectures can learn from these simulations to speed up scientific discovery and engineering processes. Most of these architectures are trained in a supervised manner. They require tremendous amounts of data from simulations that are slow to generate and memory greedy. In this article, we present our ongoing work to design a training framework that alleviates those bottlenecks. It generates data in parallel with the training process. Such simultaneity induces a bias in the data available during the training. We present a strategy to mitigate this bias with a memory buffer. We test our framework on the multi-parametric Lorenz's attractor. We show the benefit of our framework compared to offline training and the success of our data bias mitigation strategy to capture the complex chaotic dynamics of the system.
- 5 May 2022
- Published by Springer Nature
- p. 113-136
Unlocking Large Scale Uncertainty Quantification with In Transit Iterative Statistics
- 5 May 2022
- Published by Springer Nature
- p. 113-136
Unlocking Large Scale Uncertainty Quantification with In Transit Iterative Statistics
- Open Access
A Visual Sensitivity Analysis for Parameter-Augmented Ensembles of Curves
Engineers and computational scientists often study the behavior of their simulations by repeated solutions with variations in their parameters, which can be for instance boundary values or initial conditions. Through such simulation ensembles, uncertainty in a solution is studied as a function of the various input parameters. Solutions of numerical simulations are often temporal functions, spatial maps or spatio-temporal outputs. The usual way to deal with such complex outputs is to limit the analysis to several probes in the temporal/spatial domain. This leads to smaller and more tractable ensembles of functional outputs (curves) with their associated input parameters: augmented ensembles of curves. This article describes a system for the interactive exploration and analysis of such augmented ensembles. Descriptive statistics on the functional outputs are performed by Principal Component Analysis projection, kernel density estimation and the computation of High Density Regions. This makes possible the calculation of functional quantiles and outliers. Brushing and linking the elements of the system allows in-depth analysis of the ensemble. The system allows for functional descriptive statistics, cluster detection and finally for the realization of a visual sensitivity analysis via cobweb plots. We present two synthetic examples and then validate our approach in an industrial use-case concerning a marine current study using a hydraulic solver.
Open AccessA Visual Sensitivity Analysis for Parameter-Augmented Ensembles of Curves
Engineers and computational scientists often study the behavior of their simulations by repeated solutions with variations in their parameters, which can be for instance boundary values or initial conditions. Through such simulation ensembles, uncertainty in a solution is studied as a function of the various input parameters. Solutions of numerical simulations are often temporal functions, spatial maps or spatio-temporal outputs. The usual way to deal with such complex outputs is to limit the analysis to several probes in the temporal/spatial domain. This leads to smaller and more tractable ensembles of functional outputs (curves) with their associated input parameters: augmented ensembles of curves. This article describes a system for the interactive exploration and analysis of such augmented ensembles. Descriptive statistics on the functional outputs are performed by Principal Component Analysis projection, kernel density estimation and the computation of High Density Regions. This makes possible the calculation of functional quantiles and outliers. Brushing and linking the elements of the system allows in-depth analysis of the ensemble. The system allows for functional descriptive statistics, cluster detection and finally for the realization of a visual sensitivity analysis via cobweb plots. We present two synthetic examples and then validate our approach in an industrial use-case concerning a marine current study using a hydraulic solver.
- 1 December 2019
- Published by ASME International in Journal of Verification, Validation and Uncertainty Quantification
- Vol. 4 (4)
A Visual Sensitivity Analysis for Parameter-Augmented Ensembles of Curves
Engineers and computational scientists often study the behavior of their simulations by repeated solutions with variations in their parameters, which can be, for instance, boundary values or initial conditions. Through such simulation ensembles, uncertainty in a solution is studied as a function of various input parameters. Solutions of numerical simulations are often temporal functions, spatial maps, or spatio-temporal outputs. The usual way to deal with such complex outputs is to limit the analysis to several probes in the temporal/spatial domain. This leads to smaller and more tractable ensembles of functional outputs (curves) with their associated input parameters: augmented ensembles of curves. This article describes a system for the interactive exploration and analysis of such augmented ensembles. Descriptive statistics on the functional outputs are performed by principal component analysis (PCA) projection, kernel density estimation, and the computation of high density regions. This makes possible the calculation of functional quantiles and outliers. Brushing and linking the elements of the system allows in-depth analysis of the ensemble. The system allows for functional descriptive statistics, cluster detection, and finally, for the realization of a visual sensitivity analysis via cobweb plots. We present two synthetic examples and then validate our approach in an industrial use-case concerning a marine current study using a hydraulic solver.
- 1 December 2019
- Published by ASME International in Journal of Verification, Validation and Uncertainty Quantification
- Vol. 4 (4)
A Visual Sensitivity Analysis for Parameter-Augmented Ensembles of Curves
Engineers and computational scientists often study the behavior of their simulations by repeated solutions with variations in their parameters, which can be, for instance, boundary values or initial conditions. Through such simulation ensembles, uncertainty in a solution is studied as a function of various input parameters. Solutions of numerical simulations are often temporal functions, spatial maps, or spatio-temporal outputs. The usual way to deal with such complex outputs is to limit the analysis to several probes in the temporal/spatial domain. This leads to smaller and more tractable ensembles of functional outputs (curves) with their associated input parameters: augmented ensembles of curves. This article describes a system for the interactive exploration and analysis of such augmented ensembles. Descriptive statistics on the functional outputs are performed by principal component analysis (PCA) projection, kernel density estimation, and the computation of high density regions. This makes possible the calculation of functional quantiles and outliers. Brushing and linking the elements of the system allows in-depth analysis of the ensemble. The system allows for functional descriptive statistics, cluster detection, and finally, for the realization of a visual sensitivity analysis via cobweb plots. We present two synthetic examples and then validate our approach in an industrial use-case concerning a marine current study using a hydraulic solver.
- 20 October 2017
- Published by Springer Nature
- p. 655-661
In-situ Visualization for Computation Workflows
- 20 October 2017
- Published by Springer Nature
- p. 655-661
In-situ Visualization for Computation Workflows
- 3 November 2014
- Published by Springer Nature
- p. 21-37
In-Situ Visualization in Computational Fluid Dynamics Using Open-Source tools: Integration of Catalyst into Code_Saturne
- 3 November 2014
- Published by Springer Nature
- p. 21-37
In-Situ Visualization in Computational Fluid Dynamics Using Open-Source tools: Integration of Catalyst into Code_Saturne