Predicting Physics in Mesh-reduced Space with Temporal Attention

Understand

Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes.

• However, due to their short temporal attention span, these models suffer from error accumulation and drift.
• In this paper, we propose a new method that captures long-term dependencies through a transformer-style temporal attention model.
• We introduce an encoder-decoder structure to summarize features and create a compact mesh representation of the system state, to allow the temporal model to operate on a low-dimensional mesh representations in a memory efficient manner.