Výsledky vyhledávání - deep convolutional autoencoder finite element nonlinear (problem OR problems)~

Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: Comparison with linear subspace techniques

Autoři: T. Kadeethum F. Ballarin Y. Choi a další

Zdroj: Advances in Water Resources. 160:104098

Témata: FOS: Computer and information sciences, Computer Science - Machine Learning, Deep convolutional autoencoder, Reduced order modeling, Numerical Analysis (math.NA), Data-driven, 01 natural sciences, Machine Learning (cs.LG), Computational Engineering, Finance, and Science (cs.CE), Finite element, 0103 physical sciences, FOS: Mathematics, Mathematics - Numerical Analysis, 0101 mathematics, Computer Science - Computational Engineering, Finance, and Science, Non-intrusive, Nonlinear problem

Přístupová URL adresa: http://arxiv.org/abs/2107.11460
https://hdl.handle.net/10807/202829
https://doi.org/10.1016/j.advwatres.2021.104098

Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning.

Autoři: Kadeethum, Teeratorn Ballarin, Francesco O'Malley, Daniel a další

Zdroj: Scientific Reports; 11/30/2022, Vol. 12 Issue 1, p1-18, 18p

Témata: SUPERVISED learning, DEEP learning, PROPER orthogonal decomposition, NATURAL heat convection, BENCHMARK problems (Computer science), POROUS materials

Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: Comparison with linear subspace techniques

Autoři: Kadeethum, T. Ballarin, Francesco Choi, Y. a další

Témata: Data-driven, Deep convolutional autoencoder, Finite element, Non-intrusive, Nonlinear problem, Reduced order modeling, Settore MAT/08 - ANALISI NUMERICA, info:eu-repo/semantics/article

URL: https://hdl.handle.net/10807/202829
info:eu-repo/semantics/altIdentifier/wos/WOS:000803685400003
volume:160
issue:NA
firstpage:104098
lastpage:N/A
issueyear:2022
journal:ADVANCES IN WATER RESOURCES

Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques

Autoři: Kadeethum, T. Ballarin, F. Choi, Y. a další

Témata: Computer Science - Computational Engineering, Finance, and Science, Computer Science - Machine Learning, Mathematics - Numerical Analysis, text

URL: http://arxiv.org/abs/2107.11460

Stochastic electrical resistivity tomography with ensemble smoother and deep convolutional autoencoders.

Autoři: Aleardi, Mattia Vinciguerra, Alessandro Stucchi, Eusebio a další

Zdroj: Near Surface Geophysics; Apr2022, Vol. 20 Issue 2, p160-177, 18p

Témata: ELECTRICAL resistance tomography, GEOPHYSICS, DEEP learning, MATHEMATICAL optimization, ITERATIVE methods (Mathematics)

Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning

Autoři: Teeratorn Kadeethum Francesco Ballarin Daniel O’Malley a další

Zdroj: Scientific Reports, Vol 12, Iss 1, Pp 1-18 (2022)

Témata: Medicine, Science

Popis souboru: electronic resource

Relation: https://doaj.org/toc/2045-2322

Přístupová URL adresa: https://doaj.org/article/8b722ad517564aca80ac5730bf04c2ee

Machine learning‐based prediction of the seismic response of fault‐crossing natural gas pipelines.

Autoři: Zhang, Wenyang Ayello, Francois Honegger, Doug a další

Zdroj: Earthquake Engineering & Structural Dynamics; Sep2023, Vol. 52 Issue 11, p3238-3255, 18p

Témata: NATURAL gas pipelines, MACHINE learning, SEISMIC response, INFRASTRUCTURE (Economics), FINITE element method, STATISTICAL models, REGRESSION analysis

Optimal approximations for the free boundary problems of the space-time fractional Black-Scholes equations using a combined physics-informed neural network.

Autoři: Song L Tan Y Yu F a další

Zdroj: Scientific reports [Sci Rep] 2024 Oct 25; Vol. 14 (1), pp. 25289. Date of Electronic Publication: 2024 Oct 25.

Způsob vydávání: Journal Article

Informace o časopise: Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: PubMed not MEDLINE; MEDLINE

Wheel impact test by deep learning: prediction of location and magnitude of maximum stress.

Autoři: Shin, Seungyeon Jin, Ah-hyeon Yoo, Soyoung a další

Zdroj: Structural & Multidisciplinary Optimization; Jan2023, Vol. 66 Issue 1, p1-20, 20p

Deep learning methods for blood flow reconstruction in a vessel with contrast enhanced x-ray computed tomography.

Autoři: Shusong H Monica S Bruno S

Zdroj: International journal for numerical methods in biomedical engineering [Int J Numer Method Biomed Eng] 2024 Jan; Vol. 40 (1), pp. e3785. Date of Electronic Publication: 2023 Oct 25.

Způsob vydávání: Journal Article

Informace o časopise: Publisher: Wiley Country of Publication: England NLM ID: 101530293 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2040-7947 (Electronic) Linking ISSN: 20407939 NLM ISO Abbreviation: Int J Numer Method Biomed Eng Subsets: MEDLINE

Výrazy ze slovníku MeSH: Deep Learning*, Tomography, X-Ray Computed/methods ; Hemodynamics ; X-Rays ; Image Processing, Computer-Assisted/methods ; Algorithms

Prediction of cross-sectional features of SPR joints based on the punch force-displacement curve using machine learning.

Autoři: Ferrándiz, Borja Daoud, Monzer Kohout, Nicolas a další

Zdroj: International Journal of Advanced Manufacturing Technology; Oct2023, Vol. 128 Issue 9/10, p4023-4034, 12p, 1 Color Photograph, 1 Black and White Photograph, 6 Charts, 10 Graphs

Témata: MACHINE learning, SPOT welding, MECHANICAL behavior of materials, RIVETED joints, FINITE element method

Manifold Learning

Autoři: David Ryckelynck Fabien Casenave Nissrine Akkari

Resource Type: eBook.

Témata: Continuum mechanics, Deep learning (Machine learning), Structural analysis (Engineering)

Categories: MATHEMATICS / Probability & Statistics / General, COMPUTERS / Artificial Intelligence / General, COMPUTERS / Mathematical & Statistical Software, SCIENCE / Physics / Mathematical & Computational, SCIENCE / Mechanics / Thermodynamics, TECHNOLOGY & ENGINEERING / Industrial Engineering

Model‐Reduced Adjoint‐Based Inversion Using Deep‐Learning: Example of Geological Carbon Sequestration Modeling.

Autoři: Xiao, Cong Zhang, Shicheng Ma, Xinfang a další

Zdroj: Water Resources Research; Jan2022, Vol. 58 Issue 1, p1-27, 27p

Témata: GEOLOGICAL carbon sequestration, MULTIPHASE flow, FINITE difference method, REDUCED-order models, GEOLOGICAL modeling, DEEP learning, MAGNITUDE (Mathematics), WORKFLOW

Nonlinear reduced-order modeling with a Graph Convolutional Autoencoder for time-domain electromagnetics

Autoři: Filippin, Carlotta Strazzullo, Maria Lanteri, Stéphane a další

Přispěvatelé: Filippin, Carlotta Strazzullo, Maria Lanteri, Stéphane a další

Témata: nanophotonique, nanophotonics électromagnétisme computationnel, réseaux de neurones, nonlinear phenomena, graph neural networks, computational electromagnetics, [MATH.MATH-NA] Mathematics [math]/Numerical Analysis [math.NA], phénomènes non linéaires, modélisation d'ordre réduit, reduced order modeling

Popis souboru: application/pdf

Přístupová URL adresa: https://hal.science/hal-04867474v1

Embedding physical knowledge in deep neural networks for predicting the phonon dispersion curves of cellular metamaterials.

Autoři: Wang, Zihan Xian, Weikang Li, Ying a další

Zdroj: Computational Mechanics; Jul2023, Vol. 72 Issue 1, p221-239, 19p

Témata: ARTIFICIAL neural networks, CONVOLUTIONAL neural networks, PHONONS, METAMATERIALS, DISPERSION (Chemistry)

Non-intrusive surrogate modeling for parametrized time-dependent partial differential equations using convolutional autoencoders.

Autoři: Nikolopoulos, Stefanos Kalogeris, Ioannis Papadopoulos, Vissarion

Zdroj: Engineering Applications of Artificial Intelligence. Mar2022, Vol. 109, pN.PAG-N.PAG. 1p.

Témata: *PARTIAL differential equations, *MONTE Carlo method, *STOCHASTIC analysis, *FINITE element method, *DEEP learning, *DECODING algorithms

Dimensionality reduction through convolutional autoencoders for fracture patterns prediction.

Autoři: Shinde, Krushna Itier, Vincent Mennesson, José a další

Zdroj: Applied Mathematical Modelling. Feb2023, Vol. 114, p94-113. 20p.

Témata: *DEEP learning, *CRACK propagation, *STRUCTURAL mechanics, *FRACTURE mechanics, *BRITTLE fractures, *PRINCIPAL components analysis, *REDUCED-order models

Deep ensemble inverse model for image-based estimation of solar cell parameters.

Autoři: Battaglia, M. Comi, E. Stadelmann, T. a další

Zdroj: APL Machine Learning; Mar2023, Vol. 1 Issue 1, p1-13, 13p

Témata: SOLAR cells, ELECTROLUMINESCENCE, CONVOLUTIONAL neural networks, DEEP learning, FABRICATION (Manufacturing)

Diagnosis of interior damage with a convolutional neural network using simulation and measurement data.

Autoři: Bao, Yanqing Mahadevan, Sankaran

Zdroj: Structural Health Monitoring; Sep2022, Vol. 21 Issue 5, p2312-2328, 17p

Témata: CONVOLUTIONAL neural networks, ARTIFICIAL neural networks, DEEP learning, STRUCTURAL health monitoring, INHOMOGENEOUS materials, SURFACE cracks

Assessment of unsteady flow predictions using hybrid deep learning based reduced-order models.

Autoři: Bukka, Sandeep Reddy Gupta, Rachit Magee, Allan Ross a další

Zdroj: Physics of Fluids. Jan2021, Vol. 33 Issue 1, p1-43. 43p.

Témata: *REDUCED-order models, *BLENDED learning, *DEEP learning, *RECURRENT neural networks, *PROPER orthogonal decomposition, *UNSTEADY flow