Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381247932> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4381247932 abstract "Deep-learning-based surrogate models provide an efficient complement to numerical simulations for subsurface flow problems such as CO$_2$ geological storage. Accurately capturing the impact of faults on CO$_2$ plume migration remains a challenge for many existing deep learning surrogate models based on Convolutional Neural Networks (CNNs) or Neural Operators. We address this challenge with a graph-based neural model leveraging recent developments in the field of Graph Neural Networks (GNNs). Our model combines graph-based convolution Long-Short-Term-Memory (GConvLSTM) with a one-step GNN model, MeshGraphNet (MGN), to operate on complex unstructured meshes and limit temporal error accumulation. We demonstrate that our approach can accurately predict the temporal evolution of gas saturation and pore pressure in a synthetic reservoir with impermeable faults. Our results exhibit a better accuracy and a reduced temporal error accumulation compared to the standard MGN model. We also show the excellent generalizability of our algorithm to mesh configurations, boundary conditions, and heterogeneous permeability fields not included in the training set. This work highlights the potential of GNN-based methods to accurately and rapidly model subsurface flow with complex faults and fractures." @default.
- W4381247932 created "2023-06-20" @default.
- W4381247932 creator A5007168661 @default.
- W4381247932 creator A5027534318 @default.
- W4381247932 creator A5033541460 @default.
- W4381247932 creator A5047662931 @default.
- W4381247932 creator A5068456167 @default.
- W4381247932 creator A5071165005 @default.
- W4381247932 date "2023-06-16" @default.
- W4381247932 modified "2023-09-23" @default.
- W4381247932 title "Learning CO$_2$ plume migration in faulted reservoirs with Graph Neural Networks" @default.
- W4381247932 doi "https://doi.org/10.48550/arxiv.2306.09648" @default.
- W4381247932 hasPublicationYear "2023" @default.
- W4381247932 type Work @default.
- W4381247932 citedByCount "0" @default.
- W4381247932 crossrefType "posted-content" @default.
- W4381247932 hasAuthorship W4381247932A5007168661 @default.
- W4381247932 hasAuthorship W4381247932A5027534318 @default.
- W4381247932 hasAuthorship W4381247932A5033541460 @default.
- W4381247932 hasAuthorship W4381247932A5047662931 @default.
- W4381247932 hasAuthorship W4381247932A5068456167 @default.
- W4381247932 hasAuthorship W4381247932A5071165005 @default.
- W4381247932 hasBestOaLocation W43812479321 @default.
- W4381247932 hasConcept C108583219 @default.
- W4381247932 hasConcept C11413529 @default.
- W4381247932 hasConcept C121684516 @default.
- W4381247932 hasConcept C132525143 @default.
- W4381247932 hasConcept C154945302 @default.
- W4381247932 hasConcept C31487907 @default.
- W4381247932 hasConcept C41008148 @default.
- W4381247932 hasConcept C50644808 @default.
- W4381247932 hasConcept C80444323 @default.
- W4381247932 hasConcept C81363708 @default.
- W4381247932 hasConceptScore W4381247932C108583219 @default.
- W4381247932 hasConceptScore W4381247932C11413529 @default.
- W4381247932 hasConceptScore W4381247932C121684516 @default.
- W4381247932 hasConceptScore W4381247932C132525143 @default.
- W4381247932 hasConceptScore W4381247932C154945302 @default.
- W4381247932 hasConceptScore W4381247932C31487907 @default.
- W4381247932 hasConceptScore W4381247932C41008148 @default.
- W4381247932 hasConceptScore W4381247932C50644808 @default.
- W4381247932 hasConceptScore W4381247932C80444323 @default.
- W4381247932 hasConceptScore W4381247932C81363708 @default.
- W4381247932 hasLocation W43812479321 @default.
- W4381247932 hasOpenAccess W4381247932 @default.
- W4381247932 hasPrimaryLocation W43812479321 @default.
- W4381247932 hasRelatedWork W2731899572 @default.
- W4381247932 hasRelatedWork W2999805992 @default.
- W4381247932 hasRelatedWork W3011074480 @default.
- W4381247932 hasRelatedWork W3116150086 @default.
- W4381247932 hasRelatedWork W3133861977 @default.
- W4381247932 hasRelatedWork W3192840557 @default.
- W4381247932 hasRelatedWork W4200173597 @default.
- W4381247932 hasRelatedWork W4291897433 @default.
- W4381247932 hasRelatedWork W4312417841 @default.
- W4381247932 hasRelatedWork W4321369474 @default.
- W4381247932 isParatext "false" @default.
- W4381247932 isRetracted "false" @default.
- W4381247932 workType "article" @default.