Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321481273> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4321481273 abstract "The application of numerical models for flood and inundation modelling has become widespread in the past decades as a result of significant improvements in computational capabilities. Computational approaches to flood forecasting have significant benefits compared to empirical approaches which estimate statistical patterns of hydrological variables from observed data. However, there is still a significant computational cost associated with numerical flood modelling at high spatio-temporal resolutions. This limitation of numerical modelling has led to the development of statistical emulator models, machine learning (ML) models designed to learn the underlying generating process of the numerical model. The data-driven approach to ML involves relying entirely upon a set of training data to inform decisions about model selection and parameterisations. Deep learning models have leveraged data-driven learning methods with improvements in hardware and an increasing abundance of data to obtain breakthroughs in various fields such as computer vision, natural language processing and autonomous driving. In many scientific and engineering problems however, the cost of obtaining data is high and so there is a need for ML models that are able to generalise in the ‘small-data’ regime common to many complex problems. In this study, to overcome extrapolation and over-fitting issues of data-driven emulators, a Physics-Informed Neural Network model is adopted for the emulation of all two-dimensional hydrodynamic models which model fluid according the shallow water equations. This study introduces a novel approach to encoding the conservation of mass into a deep learning model, with additional terms included in the optimisation criterion, acting to regularise the model, avoid over-fitting and produce more physically consistent predictions by the emulator." @default.
- W4321481273 created "2023-02-23" @default.
- W4321481273 creator A5003500959 @default.
- W4321481273 creator A5003720277 @default.
- W4321481273 creator A5076843956 @default.
- W4321481273 date "2023-05-15" @default.
- W4321481273 modified "2023-09-30" @default.
- W4321481273 title "Physics-Informed Neural Networks for Statistical Emulation of Hydrodynamical Numerical Models" @default.
- W4321481273 doi "https://doi.org/10.5194/egusphere-egu23-5445" @default.
- W4321481273 hasPublicationYear "2023" @default.
- W4321481273 type Work @default.
- W4321481273 citedByCount "0" @default.
- W4321481273 crossrefType "posted-content" @default.
- W4321481273 hasAuthorship W4321481273A5003500959 @default.
- W4321481273 hasAuthorship W4321481273A5003720277 @default.
- W4321481273 hasAuthorship W4321481273A5076843956 @default.
- W4321481273 hasBestOaLocation W43214812732 @default.
- W4321481273 hasConcept C111919701 @default.
- W4321481273 hasConcept C119857082 @default.
- W4321481273 hasConcept C132459708 @default.
- W4321481273 hasConcept C134306372 @default.
- W4321481273 hasConcept C138885662 @default.
- W4321481273 hasConcept C149810388 @default.
- W4321481273 hasConcept C154945302 @default.
- W4321481273 hasConcept C162324750 @default.
- W4321481273 hasConcept C27206212 @default.
- W4321481273 hasConcept C33923547 @default.
- W4321481273 hasConcept C41008148 @default.
- W4321481273 hasConcept C50522688 @default.
- W4321481273 hasConcept C50644808 @default.
- W4321481273 hasConcept C66024118 @default.
- W4321481273 hasConcept C74256435 @default.
- W4321481273 hasConcept C98045186 @default.
- W4321481273 hasConceptScore W4321481273C111919701 @default.
- W4321481273 hasConceptScore W4321481273C119857082 @default.
- W4321481273 hasConceptScore W4321481273C132459708 @default.
- W4321481273 hasConceptScore W4321481273C134306372 @default.
- W4321481273 hasConceptScore W4321481273C138885662 @default.
- W4321481273 hasConceptScore W4321481273C149810388 @default.
- W4321481273 hasConceptScore W4321481273C154945302 @default.
- W4321481273 hasConceptScore W4321481273C162324750 @default.
- W4321481273 hasConceptScore W4321481273C27206212 @default.
- W4321481273 hasConceptScore W4321481273C33923547 @default.
- W4321481273 hasConceptScore W4321481273C41008148 @default.
- W4321481273 hasConceptScore W4321481273C50522688 @default.
- W4321481273 hasConceptScore W4321481273C50644808 @default.
- W4321481273 hasConceptScore W4321481273C66024118 @default.
- W4321481273 hasConceptScore W4321481273C74256435 @default.
- W4321481273 hasConceptScore W4321481273C98045186 @default.
- W4321481273 hasLocation W43214812731 @default.
- W4321481273 hasLocation W43214812732 @default.
- W4321481273 hasOpenAccess W4321481273 @default.
- W4321481273 hasPrimaryLocation W43214812731 @default.
- W4321481273 hasRelatedWork W2084188009 @default.
- W4321481273 hasRelatedWork W2105508921 @default.
- W4321481273 hasRelatedWork W2349728598 @default.
- W4321481273 hasRelatedWork W2377995945 @default.
- W4321481273 hasRelatedWork W2961085424 @default.
- W4321481273 hasRelatedWork W3017054987 @default.
- W4321481273 hasRelatedWork W3033699114 @default.
- W4321481273 hasRelatedWork W4231884363 @default.
- W4321481273 hasRelatedWork W4306674287 @default.
- W4321481273 hasRelatedWork W641208093 @default.
- W4321481273 isParatext "false" @default.
- W4321481273 isRetracted "false" @default.
- W4321481273 workType "article" @default.