Aerodynamic shape optimization (ASO) is a key technique in aerodynamic design, aimed at enhancing an object's physical performance while adhering to specific constraints. Traditional ASO parameterization methods often require substantial manual tuning and are limited to surface deformations.

In a paper to be presented at the AIAA Aviation Forum ( https://infoscience.epfl.ch/record/31...) , we introduce the Deep Geometric Mapping (DeepGeo) model, a fully automatic neuralnetworkbased parameterization method for complex geometries.

DeepGeo exploits the universal approximation capability of deep networks to provide large shape deformation freedom with global shape smoothness, while achieving effective optimization in highdimensional design spaces. Additionally, DeepGeo integrates volumetric mesh deformation, simplifying the ASO pipeline. By eliminating the need for extensive datasets and hyperparameter tuning, DeepGeo significantly reduces implementation complexity and cost.

In the example in this video, the objective is to minimize the drag coefficient for a given lift coefficient, which among other things means eliminating the shockwaves shown in yellow. For more case studies, please refer to the paper.