3–5 Jun 2026
Pisa
Europe/Rome timezone

Space-time continuous pde forecasting using equivariant neural fields

5 Jun 2026, 10:30
15m
Pisa

Pisa

MS07 - Recent Advances in Data-Driven Surrogate Modeling MS07.1 - Recent Advances in Data-Driven Surrogate Modeling

Speaker

Riccardo Valperga (AI4I)

Description

Recently, Conditional Neural Fields (NeFs) have emerged as a powerful modelling paradigm for PDEs, by learning solutions as flows in the latent space of the Conditional NeF. Although benefiting from favourable properties of NeFs such as grid-agnosticity and space-time-continuous dynamics modelling, this approach limits the ability to impose known constraints of the PDE on the solutions--such as symmetries or boundary conditions--in favour of modelling flexibility. Instead, we propose a space-time continuous NeF-based solving framework that-by preserving geometric information in the latent space of the Conditional NeF-preserves known symmetries of the PDE. We show that modelling solutions as flows of pointclouds over the group of interest improves generalization and data-efficiency. Furthermore, we validate that our framework readily generalizes to unseen spatial and temporal locations, as well as geometric transformations of the initial conditions-where other NeF-based PDE forecasting methods fail-, and improve over baselines in a number of challenging geometries.

Authors

Mr David Knigge (New Theory) Mr David Wessels (University of Amsterdam)

Co-authors

Prof. Efstratios Gavves (University of Amsterdam) Prof. Erik Bekkers (University of Amsterdam) Prof. Jan-Jakob Sonke (NKI) Riccardo Valperga (AI4I) Mr Samuele Papa (EMMI AI)

Presentation materials

There are no materials yet.