3D deformable solid systems

The '3D deformable solid systems' dataset/benchmark contains simulations of three-dimensional materials that can change shape and is used to evaluate the performance of graph neural networks in terms of rollout error, conservation of quantities like energy and momentum, and generalizability to unseen system sizes.

Papers using 3D deformable solid systems (1)

Unravelling the Performance of Physics-informed Graph Neural Networks for Dynamical Systems2022 · 12 cites