Shape Optimization using Geodesic Convolutional Networks
Our ICML paper about our approach to Aerodynamic shape optimization. This new contribution using the Geometric Deep Learning methods, improves upon previously used Kriging-based surrogate models for CFD optimization.
You can find the full paper here : ICML 2018 Paper.
Online Pressure and Drag prediction with GCNN.
Optimization of a foil with control points.
Optimization of a Foil in 3D.
Finding the most aerodynamic shape around a sphere.