Computer Research and Modeling
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Computer Research and Modeling:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Computer Research and Modeling, 2021, Volume 13, Issue 4, Pages 779–792
DOI: https://doi.org/10.20537/2076-7633-2021-13-4-779-792
(Mi crm916)
 

This article is cited in 1 scientific paper (total in 1 paper)

MODELS IN PHYSICS AND TECHNOLOGY

Data-driven simulation of a two-phase flow in heterogenous porous media

A. V. Umavovskiy

National University of Oil and Gas «Gubkin University», 65 Leninsky ave., Moscow, 119991, Russia
Full-text PDF (860 kB) Citations (1)
References:
Abstract: The numerical methods used to simulate the evolution of hydrodynamic systems require the considerable use of computational resources thus limiting the number of possible simulations. The data-driven simulation technique is one promising approach to the development of heuristic models, which may speed up the study of such models. In this approach, machine learning methods are used to tune the weights of an artificial neural network that predicts the state of a physical system at a given point in time based on initial conditions. This article describes an original neural network architecture and a novel multi-stage training procedure which create a heuristic model of a two-phase flow in a heterogeneous porous medium. The neural network-based model predicts the states of the grid cells at an arbitrary timestep (within the known constraints), taking in only the initial conditions: the properties of the heterogeneous permeability of the medium and the location of sources and sinks. The proposed model requires orders of magnitude less processor time in comparison with the classical numerical method, which served as a criterion for evaluating the effectiveness of the trained model. The proposed architecture includes a number of subnets trained in various combinations on several datasets. The techniques of adversarial training and weight transfer are utilized.
Keywords: data-driven simulation, physics informed neural networks, proxy modelling, hydrodynamics, porous media, convolutional neural networks, GAN.
Received: 16.04.2021
Revised: 23.06.2021
Accepted: 30.06.2021
Document Type: Article
UDC: 532.5
Language: Russian
Citation: A. V. Umavovskiy, “Data-driven simulation of a two-phase flow in heterogenous porous media”, Computer Research and Modeling, 13:4 (2021), 779–792
Citation in format AMSBIB
\Bibitem{Uma21}
\by A.~V.~Umavovskiy
\paper Data-driven simulation of a two-phase flow in heterogenous porous media
\jour Computer Research and Modeling
\yr 2021
\vol 13
\issue 4
\pages 779--792
\mathnet{http://mi.mathnet.ru/crm916}
\crossref{https://doi.org/10.20537/2076-7633-2021-13-4-779-792}
Linking options:
  • https://www.mathnet.ru/eng/crm916
  • https://www.mathnet.ru/eng/crm/v13/i4/p779
  • This publication is cited in the following 1 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Computer Research and Modeling
    Statistics & downloads:
    Abstract page:92
    Full-text PDF :31
    References:23
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024