Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048678724> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3048678724 endingPage "109757" @default.
- W3048678724 startingPage "109757" @default.
- W3048678724 abstract "Discontinuous Galerkin Finite Element Methods (DGFEM) have been widely used for solving SN radiation transport problems in participative and non-participative media. Global matrices are not assembled when sweeping through the computational domain, but only small matrix-vector systems are assembled and solved for each cell, angle, energy group, and time step (e.g., systems with 8 independent equations for tri-linear DGFEM in 3D hexahedral cells). These systems are generally solved directly using Gaussian elimination. The computational cost of assembling and solving these local systems, repeated for each cell in the phase-space, can amount to a large fraction of the total computation time. Therefore, a Machine Learning algorithm is designed in this paper, based on Artificial Neural Networks (ANNs), to replace the assembling and solution of the local systems, enabling a sizable speed up in the solution process. The key idea is to train an ANN with a large set of solutions to random one-cell transport problems and, then, replace the assembling and solution of the local systems by the feedforward evaluation of the trained ANN in large-scale transport solvers. These ANNs are optimized to reproduce the solutions obtained in radiation transport solves, while minimizing the number of operations involved in its feedforward evaluation. It is observed that the optimized ANNs are able to reduce the compute times by a factor of ∼3.6 per source iteration, while introducing mean absolute errors between 0.5−2% in transport solutions." @default.
- W3048678724 created "2020-08-18" @default.
- W3048678724 creator A5033526491 @default.
- W3048678724 creator A5043555642 @default.
- W3048678724 date "2021-02-01" @default.
- W3048678724 modified "2023-10-11" @default.
- W3048678724 title "Sweep-Net: An Artificial Neural Network for radiation transport solves" @default.
- W3048678724 cites W2002016471 @default.
- W3048678724 cites W2013207232 @default.
- W3048678724 cites W2032542619 @default.
- W3048678724 cites W2057467722 @default.
- W3048678724 cites W2060004468 @default.
- W3048678724 cites W2063998852 @default.
- W3048678724 cites W2076118331 @default.
- W3048678724 cites W2082890708 @default.
- W3048678724 cites W2092649395 @default.
- W3048678724 cites W2095092117 @default.
- W3048678724 cites W2110804513 @default.
- W3048678724 cites W2116432164 @default.
- W3048678724 cites W2134942647 @default.
- W3048678724 cites W2137356002 @default.
- W3048678724 cites W2140196823 @default.
- W3048678724 cites W2155503253 @default.
- W3048678724 cites W2173025977 @default.
- W3048678724 cites W2371629303 @default.
- W3048678724 cites W3158334503 @default.
- W3048678724 cites W58967705 @default.
- W3048678724 doi "https://doi.org/10.1016/j.jcp.2020.109757" @default.
- W3048678724 hasPublicationYear "2021" @default.
- W3048678724 type Work @default.
- W3048678724 sameAs 3048678724 @default.
- W3048678724 citedByCount "2" @default.
- W3048678724 countsByYear W30486787242022 @default.
- W3048678724 crossrefType "journal-article" @default.
- W3048678724 hasAuthorship W3048678724A5033526491 @default.
- W3048678724 hasAuthorship W3048678724A5043555642 @default.
- W3048678724 hasBestOaLocation W30486787241 @default.
- W3048678724 hasConcept C11413529 @default.
- W3048678724 hasConcept C121332964 @default.
- W3048678724 hasConcept C126255220 @default.
- W3048678724 hasConcept C127413603 @default.
- W3048678724 hasConcept C133731056 @default.
- W3048678724 hasConcept C135628077 @default.
- W3048678724 hasConcept C154945302 @default.
- W3048678724 hasConcept C186899397 @default.
- W3048678724 hasConcept C33923547 @default.
- W3048678724 hasConcept C38858127 @default.
- W3048678724 hasConcept C41008148 @default.
- W3048678724 hasConcept C45374587 @default.
- W3048678724 hasConcept C47702885 @default.
- W3048678724 hasConcept C50644808 @default.
- W3048678724 hasConcept C97355855 @default.
- W3048678724 hasConceptScore W3048678724C11413529 @default.
- W3048678724 hasConceptScore W3048678724C121332964 @default.
- W3048678724 hasConceptScore W3048678724C126255220 @default.
- W3048678724 hasConceptScore W3048678724C127413603 @default.
- W3048678724 hasConceptScore W3048678724C133731056 @default.
- W3048678724 hasConceptScore W3048678724C135628077 @default.
- W3048678724 hasConceptScore W3048678724C154945302 @default.
- W3048678724 hasConceptScore W3048678724C186899397 @default.
- W3048678724 hasConceptScore W3048678724C33923547 @default.
- W3048678724 hasConceptScore W3048678724C38858127 @default.
- W3048678724 hasConceptScore W3048678724C41008148 @default.
- W3048678724 hasConceptScore W3048678724C45374587 @default.
- W3048678724 hasConceptScore W3048678724C47702885 @default.
- W3048678724 hasConceptScore W3048678724C50644808 @default.
- W3048678724 hasConceptScore W3048678724C97355855 @default.
- W3048678724 hasFunder F4320332186 @default.
- W3048678724 hasLocation W30486787241 @default.
- W3048678724 hasOpenAccess W3048678724 @default.
- W3048678724 hasPrimaryLocation W30486787241 @default.
- W3048678724 hasRelatedWork W1529660427 @default.
- W3048678724 hasRelatedWork W1557629110 @default.
- W3048678724 hasRelatedWork W2045727192 @default.
- W3048678724 hasRelatedWork W2090361488 @default.
- W3048678724 hasRelatedWork W2115072676 @default.
- W3048678724 hasRelatedWork W2158578859 @default.
- W3048678724 hasRelatedWork W2378760347 @default.
- W3048678724 hasRelatedWork W3121106353 @default.
- W3048678724 hasRelatedWork W4311212821 @default.
- W3048678724 hasRelatedWork W2102065768 @default.
- W3048678724 hasVolume "426" @default.
- W3048678724 isParatext "false" @default.
- W3048678724 isRetracted "false" @default.
- W3048678724 magId "3048678724" @default.
- W3048678724 workType "article" @default.