English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A computational method based on the non-linear Gaussian process (GP), knownas deep Gaussian processes (deep GPs) for uncertainty quantification &propagation in modelling of flow through heterogeneous porous media ispresented. The method is also used for reducing dimensionality of model outputand consequently emulating highly complex relationship between hydrogeologicalproperties and reduced order fluid velocity field in a tractable manner. DeepGPs are multi-layer hierarchical generalisations of GPs with multiple,infinitely wide hidden layers that are very efficient models for deep learningand modelling of high-dimensional complex systems by tackling the complexitythrough several hidden layers connected with non-linear mappings. According tothis approach, the hydrogeological data is modelled as the output of amultivariate GP whose inputs are governed by another GP such that each singlelayer is either a standard GP or the Gaussian process latent variable model. Avariational approximation framework is used so that the posterior distributionof the model outputs associated to given inputs can be analyticallyapproximated. In contrast to the other dimensionality reduction, methods thatdo not provide any information about the dimensionality of each hidden layer,the proposed method automatically selects the dimensionality of each hiddenlayer and it can be used to propagate uncertainty obtained in each layer acrossthe hierarchy. Using this, dimensionality of the full input space consists ofboth geometrical parameters of modelling domain and stochastic hydrogeologicalparameters can be simultaneously reduced without the need for anysimplifications generally being assumed for stochastic modelling of subsurfaceflow problems. It allows estimation of the flow statistics with greatly reducedcomputational efforts compared to other stochastic approaches such as MonteCarlo method.

Uncertainty Quantification of Darcy Flow through Porous Media using Deep Gaussian Process