Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092228416> ?p ?o ?g. }
- W3092228416 abstract "Mesh-based simulations are central to modeling complex physical systems in many disciplines across science and engineering. Mesh representations support powerful numerical integration methods and their resolution can be adapted to strike favorable trade-offs between accuracy and efficiency. However, high-dimensional scientific simulations are very expensive to run, and solvers and parameters must often be tuned individually to each system studied. Here we introduce MeshGraphNets, a framework for learning mesh-based simulations using graph neural networks. Our model can be trained to pass messages on a mesh graph and to adapt the mesh discretization during forward simulation. Our results show it can accurately predict the dynamics of a wide range of physical systems, including aerodynamics, structural mechanics, and cloth. The model's adaptivity supports learning resolution-independent dynamics and can scale to more complex state spaces at test time. Our method is also highly efficient, running 1-2 orders of magnitude faster than the simulation on which it is trained. Our approach broadens the range of problems on which neural network simulators can operate and promises to improve the efficiency of complex, scientific modeling tasks." @default.
- W3092228416 created "2020-10-15" @default.
- W3092228416 creator A5059792149 @default.
- W3092228416 creator A5061277347 @default.
- W3092228416 creator A5088815712 @default.
- W3092228416 creator A5089078828 @default.
- W3092228416 date "2020-10-07" @default.
- W3092228416 modified "2023-10-17" @default.
- W3092228416 title "Learning Mesh-Based Simulation with Graph Networks" @default.
- W3092228416 cites W1646289414 @default.
- W3092228416 cites W1969402485 @default.
- W3092228416 cites W1990241567 @default.
- W3092228416 cites W2004757315 @default.
- W3092228416 cites W2011194465 @default.
- W3092228416 cites W2018236969 @default.
- W3092228416 cites W2059469850 @default.
- W3092228416 cites W2086210210 @default.
- W3092228416 cites W2089858332 @default.
- W3092228416 cites W2114741274 @default.
- W3092228416 cites W2116341502 @default.
- W3092228416 cites W2131848090 @default.
- W3092228416 cites W2133132545 @default.
- W3092228416 cites W2216523920 @default.
- W3092228416 cites W227729886 @default.
- W3092228416 cites W2515505748 @default.
- W3092228416 cites W2605917215 @default.
- W3092228416 cites W2795008545 @default.
- W3092228416 cites W2885317998 @default.
- W3092228416 cites W2901474455 @default.
- W3092228416 cites W2941443959 @default.
- W3092228416 cites W2963149188 @default.
- W3092228416 cites W2963207497 @default.
- W3092228416 cites W2963504959 @default.
- W3092228416 cites W2963892986 @default.
- W3092228416 cites W2964015378 @default.
- W3092228416 cites W2965742591 @default.
- W3092228416 cites W2985630280 @default.
- W3092228416 cites W2995511918 @default.
- W3092228416 cites W2996324165 @default.
- W3092228416 cites W3012274818 @default.
- W3092228416 cites W3014178136 @default.
- W3092228416 cites W3034655405 @default.
- W3092228416 cites W3034727889 @default.
- W3092228416 cites W3035431334 @default.
- W3092228416 cites W3080930191 @default.
- W3092228416 cites W3087547017 @default.
- W3092228416 cites W3100989476 @default.
- W3092228416 cites W3123883114 @default.
- W3092228416 cites W613321901 @default.
- W3092228416 hasPublicationYear "2020" @default.
- W3092228416 type Work @default.
- W3092228416 sameAs 3092228416 @default.
- W3092228416 citedByCount "3" @default.
- W3092228416 countsByYear W30922284162021 @default.
- W3092228416 crossrefType "posted-content" @default.
- W3092228416 hasAuthorship W3092228416A5059792149 @default.
- W3092228416 hasAuthorship W3092228416A5061277347 @default.
- W3092228416 hasAuthorship W3092228416A5088815712 @default.
- W3092228416 hasAuthorship W3092228416A5089078828 @default.
- W3092228416 hasConcept C116672817 @default.
- W3092228416 hasConcept C120314980 @default.
- W3092228416 hasConcept C121332964 @default.
- W3092228416 hasConcept C127413603 @default.
- W3092228416 hasConcept C132525143 @default.
- W3092228416 hasConcept C13393347 @default.
- W3092228416 hasConcept C134306372 @default.
- W3092228416 hasConcept C146978453 @default.
- W3092228416 hasConcept C154945302 @default.
- W3092228416 hasConcept C204323151 @default.
- W3092228416 hasConcept C33923547 @default.
- W3092228416 hasConcept C41008148 @default.
- W3092228416 hasConcept C459310 @default.
- W3092228416 hasConcept C47822265 @default.
- W3092228416 hasConcept C50644808 @default.
- W3092228416 hasConcept C62520636 @default.
- W3092228416 hasConcept C73000952 @default.
- W3092228416 hasConcept C80444323 @default.
- W3092228416 hasConceptScore W3092228416C116672817 @default.
- W3092228416 hasConceptScore W3092228416C120314980 @default.
- W3092228416 hasConceptScore W3092228416C121332964 @default.
- W3092228416 hasConceptScore W3092228416C127413603 @default.
- W3092228416 hasConceptScore W3092228416C132525143 @default.
- W3092228416 hasConceptScore W3092228416C13393347 @default.
- W3092228416 hasConceptScore W3092228416C134306372 @default.
- W3092228416 hasConceptScore W3092228416C146978453 @default.
- W3092228416 hasConceptScore W3092228416C154945302 @default.
- W3092228416 hasConceptScore W3092228416C204323151 @default.
- W3092228416 hasConceptScore W3092228416C33923547 @default.
- W3092228416 hasConceptScore W3092228416C41008148 @default.
- W3092228416 hasConceptScore W3092228416C459310 @default.
- W3092228416 hasConceptScore W3092228416C47822265 @default.
- W3092228416 hasConceptScore W3092228416C50644808 @default.
- W3092228416 hasConceptScore W3092228416C62520636 @default.
- W3092228416 hasConceptScore W3092228416C73000952 @default.
- W3092228416 hasConceptScore W3092228416C80444323 @default.
- W3092228416 hasLocation W30922284161 @default.
- W3092228416 hasOpenAccess W3092228416 @default.
- W3092228416 hasPrimaryLocation W30922284161 @default.
- W3092228416 hasRelatedWork W100152577 @default.
- W3092228416 hasRelatedWork W2075657078 @default.