Hierarchical equivariant graph neural networks for forecasting collective motion in vortex clusters and microswimmers
Open Access
- 20 November 2025
- journal article
- research article
- Published by Springer Nature in Communications Physics
- Vol. 8 (1)
Abstract
Data-driven modeling of collective dynamics is a challenging problem because emergent phenomena in multi-agent systems are often shaped by short- and long-range interactions among individuals. For example, in bird flocks and fish schools, flow coupling plays a crucial role in emergent collective behavior. Such collective motion can be modeled using graph neural networks (GNNs), but GNNs struggle when graphs become large and often fail to capture long-range interactions. Here, we construct hierarchical and equivariant GNNs, and show that these GNNs accurately predict local and global behavior in systems with collective motion. As representative examples, we apply this approach to simulations of clusters of point vortices and populations of microswimmers. In these systems, our approach is more accurate and faster than a fully-connected GNN. Specifically, only our approach conserves the Hamiltonian for the point vortices and only our approach predicts the transition from aggregation to swirling for the microswimmers.Keywords
All Related Versions
Funding Information
- U.S. Department of War (N00014-22-1-2798)
This publication has 60 references indexed in Scilit:
- Graph neural network-accelerated Lagrangian fluid simulationComputers & Graphics, 2022
- Examples of Two-Dimensional Flow Modeling2019
- Extremal Graph Theory2017
- Pursuit and Synchronization in Hydrodynamic DipolesJournal of Nonlinear Science, 2015
- Reduction of continuous symmetries of chaotic flows by the method of slicesCommunications in Nonlinear Science and Numerical Simulation, 2012
- Schooling Behavior of Light‐Powered Autonomous Micromotors in WaterAngewandte Chemie International Edition, 2009
- Empirical investigation of starling flocks: a benchmark study in collective animal behaviourAnimal Behaviour, 2008
- Resolving the sign ambiguity in the singular value decompositionJournal of Chemometrics, 2008
- Point vortex model of the unsteady separated flow past a semi-infinite plate with transverse motionFluid Dynamics Research, 1993
- A fast algorithm for particle simulationsJournal of Computational Physics, 1987