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 fully-convolutional neural-network model is used to predict the streamwisevelocity fields at several wall-normal locations by taking as input thestreamwise and spanwise wall-shear-stress planes in a turbulent open channelflow. The training data are generated by performing a direct numericalsimulation (DNS) at a friction Reynolds number of $Re_{\tau}=180$. Variousnetworks are trained for predictions at three inner-scaled locations ($y^+ =15,~30,~50$) and for different time steps between input samples $\Deltat^{+}_{s}$. The inherent non-linearity of the neural-network model enables abetter prediction capability than linear methods, with a lower error in boththe instantaneous flow fields and turbulent statistics. Using a dataset withhigher $\Delta t^+_{s}$ improves the generalization at all the consideredwall-normal locations, as long as the network capacity is sufficient togeneralize over the dataset. The use of a multiple-output network, withparallel dedicated branches for two wall-normal locations, does not provide anyimprovement over two separated single-output networks, other than a moderatesaving in training time. Training time can be effectively reduced, by a factorof 4, via a transfer learning method that initializes the network parametersusing the optimized parameters of a previously-trained network.

Prediction of wall-bounded turbulence from wall quantities using convolutional neural networks