Register now After registration you will be able to apply for this opportunity online.
Master Thesis - Graph Neural Networks for Granular Mechanics
Granular materials form complex networks of force chains arising from frictional interactions between particles. Under applied shear, this network of contacts can undergo complex topological and geometrical rearrangements. The connection between these grain-scale patterns and the macroscopic behavior of the material is still a field of active research. In this project we will employ Graph Neural Networks (GNNs) to shed light on these processes, focusing on the regime where granular materials approach unjamming and failure. The models will be trained on data from high fidelity discrete element simulations as well as experimental measurements with grain-scale resolution.
GNN_For_Granular_Mechanics.pdf
