Graph convolutional networks applied to unstructured flow field data

Many scientific and engineering processes produce spatially unstructured data. However, most data-driven models require a feature matrix that enforces both a set number and order of features for each sample. They thus cannot be easily constructed for an unstructured dataset. Therefore, a graph based data-driven model to perform inference on fields defined on an unstructured mesh, using a graph convolutional neural network (GCNN) is presented. The ability of the method to predict global properties from spatially irregular measurements with high accuracy is demonstrated by predicting the drag force associated with laminar flow around airfoils from scattered velocity measurements. The network can infer from field samples at different resolutions, and is invariant to the order in which the measurements within each sample are presented. The GCNN method, using inductive convolutional layers and adaptive pooling, is able to predict this quantity with a validation R (2) above 0.98, and a Normalized Mean Squared Error below 0.01, without relying on spatial structure.

Automated summary

The method utilizes a graph convolutional neural network to infer fields on unstructured meshes, demonstrating the accurate prediction of global properties from spatially irregular measurements, such as predicting drag force around airfoils from scattered velocity measurements.