skip to main content
Idioma:

3D multi-physics uncertainty quantification using physics-based machine learning

Degen, Denise ; Cacace, Mauro ; Wellmann, Florian

Scientific reports, 2022-10, Vol.12 (1), p.17491-17491, Article 17491 [Periódico revisado por pares]

England: Nature Publishing Group

Texto completo disponível

Citações Citado por
  • Título:
    3D multi-physics uncertainty quantification using physics-based machine learning
  • Autor: Degen, Denise ; Cacace, Mauro ; Wellmann, Florian
  • Assuntos: Computer applications ; Learning algorithms ; Machine Learning ; Partial differential equations ; Physics ; Uncertainty
  • É parte de: Scientific reports, 2022-10, Vol.12 (1), p.17491-17491, Article 17491
  • Notas: ObjectType-Article-1
    SourceType-Scholarly Journals-1
    ObjectType-Feature-2
    content type line 23
  • Descrição: Quantitative predictions of the physical state of the Earth's subsurface are routinely based on numerical solutions of complex coupled partial differential equations together with estimates of the uncertainties in the material parameters. The resulting high-dimensional problems are computationally prohibitive even for state-of-the-art solver solutions. In this study, we introduce a hybrid physics-based machine learning technique, the non-intrusive reduced basis method, to construct reliable, scalable, and interpretable surrogate models. Our approach, to combine physical process models with data-driven machine learning techniques, allows us to overcome limitations specific to each individual component, and it enables us to carry out probabilistic analyses, such as global sensitivity studies and uncertainty quantification for real-case non-linearly coupled physical problems. It additionally provides orders of magnitude computational gain, while maintaining an accuracy higher than measurement errors. Although in this study we use a thermo-hydro-mechanical reservoir application to illustrate these features, all the theory described is equally valid and applicable to a wider range of geoscientific applications.
  • Editor: England: Nature Publishing Group
  • Idioma: Inglês
Links
Voltar para lista de resultados
Ir para página anteriorAnterior Resultado  7 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.