Decomposing heterogeneous dynamical systems with graph neural networks

janelia7_blocks-janelia7_biblio_header | block

arXiv. 2024 Jul 27;. doi: 10.48550/arXiv.2407.19160

Decomposing heterogeneous dynamical systems with graph neural networks Saalfeld Lab

Allier C, Schneider MC, Innerberger M, Heinrich L, Bogovic JA, Saalfeld S

janelia7_blocks-janelia7_biblio_abstract | block

Abstract

Natural physical, chemical, and biological dynamical systems are often complex, with heterogeneous components interacting in diverse ways. We show that graph neural networks can be designed to jointly learn the interaction rules and the structure of the heterogeneity from data alone. The learned latent structure and dynamics can be used to virtually decompose the complex system which is necessary to parameterize and infer the underlying governing equations. We tested the approach with simulation experiments of moving particles and vector fields that interact with each other. While our current aim is to better understand and validate the approach with simulated data, we anticipate it to become a generally applicable tool to uncover the governing rules underlying complex dynamics observed in nature.

janelia7_blocks-janelia7_biblio_authors | block

janelia7_blocks-janelia7_biblio_tools | block

Main Menu (Mobile)- Block

Main Menu - Block

Decomposing heterogeneous dynamical systems with graph neural networks

Abstract

Janelia Authors