An active learning approach for improving the performance of equilibrium based chemical simulations - Archive ouverte HAL Access content directly
Journal Articles Computational Geosciences Year : 2022

An active learning approach for improving the performance of equilibrium based chemical simulations

(1, 2) , (1) , (2) , (2)
1
2

Abstract

In this paper, we propose a novel sequential data-driven method for dealing with equilibrium based chemical simulations, which can be seen as a specific machine learning approach called active learning. The underlying idea of our approach is to consider the function to estimate as a sample of a Gaussian process which allows us to compute the global uncertainty on the function estimation. Thanks to this estimation and with almost no parameter to tune, the proposed method sequentially chooses the most relevant input data at which the function to estimate has to be evaluated to build a surrogate model. Hence, the number of evaluations of the function to estimate is dramatically limited. Our active learning method is validated through numerical experiments and applied to a complex chemical system commonly used in geoscience.
Fichier principal
Vignette du fichier
ms.pdf (6.87 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03396819 , version 1 (11-03-2022)

Identifiers

Cite

Mary Savino, Céline Lévy-Leduc, Marc Leconte, Benoit Cochepin. An active learning approach for improving the performance of equilibrium based chemical simulations. Computational Geosciences, 2022, 26, pp.365-380. ⟨10.1007/s10596-022-10130-0⟩. ⟨hal-03396819⟩
106 View
37 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More