Graph Convolutional Neural Networks for Body Force Prediction

Abstract

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.

References in corpus (17)

• Neural Message Passing for Quantum Chemistry
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Solving high-dimensional partial differential equations using deep learning
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• DOLFIN: Automated Finite Element Computing
• Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• Learning to Simulate Complex Physics with Graph Networks
• Towards Sparse Hierarchical Graph Classifiers
• A Spectral Clustering Approach to Lagrangian Vortex Detection
• Deep learning observables in computational fluid dynamics
• Experimental velocity data estimation for imperfect particle images using machine learning
• Deep Learning the Physics of Transport Phenomena
• An Efficient Deep Learning Technique for the Navier-Stokes Equations: Application to Unsteady Wake Flow Dynamics
• Coherent structure coloring: identification of coherent structures from sparse data using graph theory
• Meshfree Methods on Manifolds for Hydrodynamic Flows on Curved Surfaces: A Generalized Moving Least-Squares (GMLS) Approach
• Network community-based model reduction for vortical flows

Cited by in corpus (3)

• On the use of graph neural networks and shape-function-based gradient computation in the deep energy method
• Flow Completion Network: Inferring the Fluid Dynamics from Incomplete Flow Information using Graph Neural Networks
• Reconstructing three-dimensional bluff body wake from sectional flow fields with convolutional neural networks