Geometry-Informed Neural Operator Transformer
This provides a machine-learning-based surrogate model for faster simulations in computational physics and engineering, though it appears incremental as it combines existing transformer and neural operator frameworks.
The paper tackles the problem of efficiently simulating partial differential equations on arbitrary geometries by introducing the Geometry-Informed Neural Operator Transformer (GINOT), which integrates transformers with neural operators to achieve high accuracy and strong generalization on complex 2D and 3D datasets.
Machine-learning-based surrogate models offer significant computational efficiency and faster simulations compared to traditional numerical methods, especially for problems requiring repeated evaluations of partial differential equations. This work introduces the Geometry-Informed Neural Operator Transformer (GINOT), which integrates the transformer architecture with the neural operator framework to enable forward predictions on arbitrary geometries. GINOT employs a sampling and grouping strategy together with an attention mechanism to encode surface point clouds that are unordered, exhibit non-uniform point densities, and contain varying numbers of points for different geometries. The geometry information is seamlessly integrated with query points in the solution decoder through the attention mechanism. The performance of GINOT is validated on multiple challenging datasets, showcasing its high accuracy and strong generalization capabilities for complex and arbitrary 2D and 3D geometries.