Boundary Graph Neural Networks for 3D Simulations


  • Andreas Mayr Johannes Kepler University Linz, Linz, Austria
  • Sebastian Lehner Johannes Kepler University Linz, Linz, Austria
  • Arno Mayrhofer DCS Computing GmbH, Linz, Austria
  • Christoph Kloss DCS Computing GmbH, Linz, Austria
  • Sepp Hochreiter Johannes Kepler University Linz, Linz, Austria Institute of Advanced Research in Artificial Intelligence (IARAI), Vienna, Austria
  • Johannes Brandstetter Johannes Kepler University Linz, Linz, Austria



ML: Applications, APP: Natural Sciences, KRR: Applications, KRR: Geometric, Spatial, and Temporal Reasoning, ML: Deep Neural Architectures, ML: Graph-based Machine Learning


The abundance of data has given machine learning considerable momentum in natural sciences and engineering, though modeling of physical processes is often difficult. A particularly tough problem is the efficient representation of geometric boundaries. Triangularized geometric boundaries are well understood and ubiquitous in engineering applications. However, it is notoriously difficult to integrate them into machine learning approaches due to their heterogeneity with respect to size and orientation. In this work, we introduce an effective theory to model particle-boundary interactions, which leads to our new Boundary Graph Neural Networks (BGNNs) that dynamically modify graph structures to obey boundary conditions. The new BGNNs are tested on complex 3D granular flow processes of hoppers, rotating drums and mixers, which are all standard components of modern industrial machinery but still have complicated geometry. BGNNs are evaluated in terms of computational efficiency as well as prediction accuracy of particle flows and mixing entropies. BGNNs are able to accurately reproduce 3D granular flows within simulation uncertainties over hundreds of thousands of simulation timesteps. Most notably, in our experiments, particles stay within the geometric objects without using handcrafted conditions or restrictions.




How to Cite

Mayr, A., Lehner, S., Mayrhofer, A., Kloss, C., Hochreiter, S., & Brandstetter, J. (2023). Boundary Graph Neural Networks for 3D Simulations. Proceedings of the AAAI Conference on Artificial Intelligence, 37(8), 9099-9107.



AAAI Technical Track on Machine Learning III