Groundwater Contaminant Transport Solved by Monte Carlo Methods Accelerated by Deep Learning Meta-model

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F22%3A00009886" target="_blank" >RIV/46747885:24220/22:00009886 - isvavai.cz</a>

Result on the web

<a href="https://www.mdpi.com/2076-3417/12/15/7382" target="_blank" >https://www.mdpi.com/2076-3417/12/15/7382</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/app12157382" target="_blank" >10.3390/app12157382</a>

Result language

angličtina

Original language name

Groundwater Contaminant Transport Solved by Monte Carlo Methods Accelerated by Deep Learning Meta-model

Original language description

Groundwater contaminant transport modeling is a vitally important topic. Since modeled processes include uncertainties, Monte Carlo methods are adopted to obtain some statistics. However, accurate models have a substantial computational cost. This drawback can be overcome by employing the multilevel Monte Carlo method (MLMC) or approximating the original model using a meta-model. We combined both of these approaches. A stochastic model is substituted with a deep learning meta-model that consists of a graph convolutional neural network and a feed-forward neural network. This meta-model can approximate models solved on unstructured meshes. The meta-model within the standard Monte Carlo method can bring significant computational cost savings. Nevertheless, the meta-model must be highly accurate to obtain similar errors as when using the original model. Proposed MLMC with the new lowest-accurate level of meta-models can reduce total computational costs, and the accuracy of the meta-model does not have to be so high. The size of the computational cost savings depends on the cost distribution across MLMC levels. Our approach is especially efficacious when the dominant computational cost is on the lowest-accuracy MLMC level. Depending on the number of estimated moments, we can reduce computational costs by up to ca. 25% while maintaining the accuracy of estimates.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

21100 - Other engineering and technologies

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2022

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

APPLIED SCIENCES-BASEL

ISSN

2076-3417

e-ISSN

—

Volume of the periodical

12

Issue of the periodical within the volume

15

Country of publishing house

CH - SWITZERLAND

Number of pages

14

Pages from-to

—

UT code for WoS article

000839287100001

EID of the result in the Scopus database

2-s2.0-85136963098