Physics-informed reduced order model with conditional neural fields
This work addresses computational challenges in solving parametrized PDEs for scientific and engineering applications, but it is incremental as it builds on existing neural field and physics-informed methods.
The study tackled approximating solutions of parametrized partial differential equations (PDEs) by developing the CNF-ROM framework, which combines a parametric neural ODE and a decoder with physics-informed learning, and validated it through parameter and temporal extrapolation and comparisons with analytical solutions.
This study presents the conditional neural fields for reduced-order modeling (CNF-ROM) framework to approximate solutions of parametrized partial differential equations (PDEs). The approach combines a parametric neural ODE (PNODE) for modeling latent dynamics over time with a decoder that reconstructs PDE solutions from the corresponding latent states. We introduce a physics-informed learning objective for CNF-ROM, which includes two key components. First, the framework uses coordinate-based neural networks to calculate and minimize PDE residuals by computing spatial derivatives via automatic differentiation and applying the chain rule for time derivatives. Second, exact initial and boundary conditions (IC/BC) are imposed using approximate distance functions (ADFs) [Sukumar and Srivastava, CMAME, 2022]. However, ADFs introduce a trade-off as their second- or higher-order derivatives become unstable at the joining points of boundaries. To address this, we introduce an auxiliary network inspired by [Gladstone et al., NeurIPS ML4PS workshop, 2022]. Our method is validated through parameter extrapolation and interpolation, temporal extrapolation, and comparisons with analytical solutions.