A Latent space solver for PDE generalization
This work addresses the problem of PDE generalization for engineering applications, but it appears incremental as it builds on existing methods with a hybrid approach.
The authors tackled the problem of solving partial differential equations (PDEs) by proposing a hybrid solver that operates in a latent space, using iterative inferencing and solution initialization to improve generalization, and tested it on an engineering case where it generalized well to several PDE conditions.
In this work we propose a hybrid solver to solve partial differential equation (PDE)s in the latent space. The solver uses an iterative inferencing strategy combined with solution initialization to improve generalization of PDE solutions. The solver is tested on an engineering case and the results show that it can generalize well to several PDE conditions.