Paul Laiu

Dimension Bridging for 3D RANS with Neural Network Accelerated Gaussian Functional Regression

This work uses Gaussian Functional Regression to learn a correction to a 2D Reynolds-Averaged Navier-Stokes model to predict the aerodynamic coefficients from a 3D RANS model and proposes a novel neural network accelerated kernel, which offers predictions in good agreement while speeding up evaluations by millions of t...